MagicWand能自动理解用户偏好，生成并评估更符合心意的AI内容。
MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference
- 基于用户偏好数据自动优化提示词
- 在12万+标注任务中表现优于基线模型
- 适合需要个性化内容生成的创作者
AIGC模型在图像和视频生成方面取得显著进展，但用户仍难以获得符合自身偏好的内容，主要受限于难以撰写详细提示词以及缺乏偏好记忆机制。为此，我们构建了包含图像、视频及风格描述的大型数据集UniPrefer-100K。基于该数据集，提出通用生成与评估代理MagicWand，其可依据用户偏好优化提示词，利用先进生成模型产出高质量内容，并实施对齐偏好的评估与迭代优化。同时，引入首个大规模基准UniPreferBench，涵盖12万余条标注，用于评估多样化AIGC任务中的偏好对齐效果。在UniPreferBench上的实验表明，MagicWand在多种场景下均能持续生成并评估出与用户偏好高度一致的内容。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。