ImageGem：面向生成模型个性化的真实场景生成式图像交互数据集
ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization
AI总结：
该研究推出包含5.7万用户真实交互数据的ImageGem数据集，用于解决生成模型个性化缺乏细粒度真实偏好标注的问题，还提出潜在权重空间编辑扩散模型的端到端框架，开启生成模型个性化新范式。
摘要：
我们推出ImageGem（真实场景生成式图像交互数据集），用于研究能够理解细粒度个体偏好的生成模型。我们认为，阻碍此类生成模型发展的核心挑战是缺乏真实场景下的细粒度用户偏好标注。该数据集包含来自5.7万名用户的真实交互数据，这些用户共构建了24.2万个定制化LoRA（低秩适配）模型、撰写了300万条文本提示词并生成了500万张生成图像。借助数据集中的用户偏好标注，我们能够训练出性能更优的偏好对齐模型。此外，利用个体用户偏好，我们探究了检索模型与视觉语言模型在个性化图像检索和生成模型推荐任务上的表现。最后，我们提出一种端到端框架，可在潜在权重空间中编辑定制化扩散模型，使其与个体用户偏好对齐。研究结果表明，ImageGem数据集首次为生成模型个性化提供了一种新范式。
英文摘要：
We introduce ImageGem, a dataset for studying generative models that understand fine-grained individual preferences. We posit that a key challenge hindering the development of such a generative model is the lack of in-the-wild and fine-grained user preference annotations. Our dataset features real-world interaction data from 57K users, who collectively have built 242K customized LoRAs, written 3M text prompts, and created 5M generated images. With user preference annotations from our dataset, we were able to train better preference alignment models. In addition, leveraging individual user preference, we investigated the performance of retrieval models and a vision-language model on personalized image retrieval and generative model recommendation. Finally, we propose an end-to-end framework for editing customized diffusion models in a latent weight space to align with individual user preferences. Our results demonstrate that the ImageGem dataset enables, for the first time, a new paradigm for generative model personalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
