Metraipolis › archive › dc_7902e9bb1fc4
Personalized Image Generation with Reasoning and Reflection — arXiv:2610.00737
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00737
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:10:58.593Z
- SHA-256 of the archived text
f67cd273698428f40a93725dd85c82cf1b6f25d8cd8b6162f87a87856f094439- Stable URL of this page
https://metraipolis.com/documento/dc_7902e9bb1fc4
How to cite
Personalized Image Generation with Reasoning and Reflection — arXiv:2610.00737 — arXiv (en), https://arxiv.org/abs/2610.00737 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7902e9bb1fc4 (Metraipolis archive dc_7902e9bb1fc4, sha256 f67cd273698428f40a93725dd85c82cf1b6f25d8cd8b6162f87a87856f094439)
BibTeX
@misc{dc7902e9bb1fc4,
title = {Personalized Image Generation with Reasoning and Reflection — arXiv:2610.00737},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00737},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7902e9bb1fc4; sha256 f67cd273698428f40a93725dd85c82cf1b6f25d8cd8b6162f87a87856f094439},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00737. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.00737 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T10:21:28.106Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).