Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.18433 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915566515650560 |
|---|---|
| author | Guo, Yuanhe Xie, Linxi Chen, Zhuoran Yu, Kangrui Po, Ryan Yang, Guandao Wetztein, Gordon Wen, Hongyi |
| author_facet | Guo, Yuanhe Xie, Linxi Chen, Zhuoran Yu, Kangrui Po, Ryan Yang, Guandao Wetztein, Gordon Wen, Hongyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization Guo, Yuanhe Xie, Linxi Chen, Zhuoran Yu, Kangrui Po, Ryan Yang, Guandao Wetztein, Gordon Wen, Hongyi Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval 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. |
| title | ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2510.18433 |