Mirror in the Model: Ad Banner Image Generation via Reflective Multi-LLM and Multi-modal Agents
Authors:
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 246-266
Abstract
Zhao Wang, Bowen Chen, Yotaro Shimose, Sota Moriyama, Heng Wang, Shingo Takamatsu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.Keywords
This publication has 5 references indexed in Scilit:
- Talk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent SystemsIEEE Transactions on Artificial Intelligence, 2026
- BannerAgency: Advertising Banner Design with Multimodal LLM Agents2025
- Idea2Img: Iterative Self-refinement with GPT-4V for Automatic Image Design and Generation2024
- AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation2023
- Self-Refine: Iterative Refinement with Self-Feedback2023