HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 6 天前AI 评分37
基于推理与反思的个性化图像生成：PEARL 与用户历史基准
AI 导读
研究者提出首个基于用户历史（评论、帖子、图片、caption 与元数据）的个性化图像生成统一基准，包含个性化场景生成与个性化创意生成两项任务及多轴评测协议。同时提出 PEARL，将多模态推理器与冻结的图像生成器耦合为交错的"推理-反思"循环，并用差分数据奖励优化，在两项任务上平均提升 15% 的个性化指标。
正文
Authors:Bo Ni, Ngoc N. Tran, Qinwen Ge, Franck Dernoncourt, Seunghyun Yoon, Samyadeep Basu, Sungchul Kim, Puneet Mathur, Nedim Lipka, Tong Yu, Yu Wang, Ryan A. Rossi, Tyler Derr
Abstract:Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a user's personal context is much richer, comprising reviews, posts, images, captions, and metadata accumulated over time. A truly personalized generator should leverage this history to produce images aligned with the user's lifestyle and aesthetic preferences. To this end, we introduce the first unified benchmark for personalized image generation from user histories. The benchmark comprises two complementary tasks and a multi-axis evaluation protocol that assesses target fidelity, visual quality, user distinguishability, semantic alignment with the user's history, and task-specific utility. Grounded in real-world e-commerce and social media settings, the benchmark includes: (1) Personalized Scene Generation, which places a given object in a scene that reflects a user's preferences and lifestyle, motivated by personalized product presentation; and (2) Personalized Creative Generation, which generates a novel image on a specified topic that is faithful to a user's aesthetic and visual identity, motivated by social media content creation. We further propose PEARL, which couples a multimodal reasoner with a frozen image generator in an interleaved reason-reflect loop optimized with differential data reward. Across both tasks, PEARL outperforms strong baselines, achieving an average improvement of 15% across personalization metrics.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.00737 [cs.CV] |
| (or arXiv:2610.00737v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00737 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bo Ni [view email]
[v1]
Wed, 30 Sep 2026 21:30:26 UTC (10,121 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org