Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.18352 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909919671746560 |
|---|---|
| author | Xu, Zitong Shen, Dake Du, Yaosong Hao, Kexiang Huang, Jinghan Huang, Xiande |
| author_facet | Xu, Zitong Shen, Dake Du, Yaosong Hao, Kexiang Huang, Jinghan Huang, Xiande |
| contents | Recent advances in AIGC (Artificial Intelligence Generated Content) models have enabled significant progress in image and video generation. However, users still struggle to obtain content that aligns with their preferences due to the difficulty of crafting detailed prompts and the lack of mechanisms to retain their preferences. To address these challenges, we construct \textbf{UniPrefer-100K}, a large-scale dataset comprising images, videos, and associated text that describes the styles users tend to prefer. Based on UniPrefer-100K, we propose \textbf{MagicWand}, a universal generation and evaluation agent that enhances prompts based on user preferences, leverages advanced generation models for high-quality content, and applies preference-aligned evaluation and refinement. In addition, we introduce \textbf{UniPreferBench}, the first large-scale benchmark with over 120K annotations for assessing user preference alignment across diverse AIGC tasks. Experiments on UniPreferBench demonstrate that MagicWand consistently generates content and evaluations that are well aligned with user preferences across a wide range of scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18352 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference Xu, Zitong Shen, Dake Du, Yaosong Hao, Kexiang Huang, Jinghan Huang, Xiande Computer Vision and Pattern Recognition Recent advances in AIGC (Artificial Intelligence Generated Content) models have enabled significant progress in image and video generation. However, users still struggle to obtain content that aligns with their preferences due to the difficulty of crafting detailed prompts and the lack of mechanisms to retain their preferences. To address these challenges, we construct \textbf{UniPrefer-100K}, a large-scale dataset comprising images, videos, and associated text that describes the styles users tend to prefer. Based on UniPrefer-100K, we propose \textbf{MagicWand}, a universal generation and evaluation agent that enhances prompts based on user preferences, leverages advanced generation models for high-quality content, and applies preference-aligned evaluation and refinement. In addition, we introduce \textbf{UniPreferBench}, the first large-scale benchmark with over 120K annotations for assessing user preference alignment across diverse AIGC tasks. Experiments on UniPreferBench demonstrate that MagicWand consistently generates content and evaluations that are well aligned with user preferences across a wide range of scenarios. |
| title | MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.18352 |