Metraipolis › archive › dc_c9d3b210fbce

PailitaoGR: Latent Think-with-Images for Generative Image Retrieval — arXiv:2608.26658

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26658
License (as archived)
CC0-1.0
Archived
2026-10-17T14:26:16.260Z
SHA-256 of the archived text
b18bdded6b32006baa8fd95e749a2e27aeb322a8fd2d816ac1a429b5c9e6e343
Stable URL of this page
https://metraipolis.com/documento/dc_c9d3b210fbce

How to cite

PailitaoGR: Latent Think-with-Images for Generative Image Retrieval — arXiv:2608.26658 — arXiv (en), https://arxiv.org/abs/2608.26658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9d3b210fbce (Metraipolis archive dc_c9d3b210fbce, sha256 b18bdded6b32006baa8fd95e749a2e27aeb322a8fd2d816ac1a429b5c9e6e343)
BibTeX
@misc{dcc9d3b210fbce,
  title = {PailitaoGR: Latent Think-with-Images for Generative Image Retrieval — arXiv:2608.26658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9d3b210fbce; sha256 b18bdded6b32006baa8fd95e749a2e27aeb322a8fd2d816ac1a429b5c9e6e343},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image search, however, is nontrivial because real-world query images contain diverse information, including the search target, useful auxiliary evidence, and irrelevant visual content. This requires the model to identify and focus on the search target while selectively utilizing auxiliary evidence. In this paper, we propose \textbf{PailitaoGR}, a \emph{Latent Think-with-Images} method for generative image retrieval, which internalizes target-focused perception and selective auxiliary-evidence utilization into a the generative retrieval model, enabling \textit{Zooming without Cropping} and \textit{Reading without OCR}. Specifically, we design a target-focused perception mechanism that identifies and enhances visual tokens of the search target, consisting of a target Enhancer and a learning strategy based on on-policy distillation and attention guidance loss, enabling the model to focus on search-target regions. We also design a selective auxiliary-evidence utilization mechanism that identifies and enhances visual tokens of auxiliary evidence, including an auxiliary enhancer and an in-capacity incremental contrastive distillation strategy, enabling the model to exploit auxiliary evidence. We construct training and validation sets sampled from real-world online image-search logs. Experiments show that our method outperforms existing baselines by an average of 13.8\%, validating its effectiveness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.26658 — 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 2026-10-17T13:16:53.650Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).