Metraipolis › archive › dc_e217f4e5a849

SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image Generation — arXiv:2611.00722

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00722
License (as archived)
CC0-1.0
Archived
2026-11-03T18:16:16.979Z
SHA-256 of the archived text
20df11f17279479cf308ad14a23c3ff26e2a0ee161d8a1593b7d642f5e2a93ac
Stable URL of this page
https://metraipolis.com/documento/dc_e217f4e5a849

How to cite

SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image Generation — arXiv:2611.00722 — arXiv (en), https://arxiv.org/abs/2611.00722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e217f4e5a849 (Metraipolis archive dc_e217f4e5a849, sha256 20df11f17279479cf308ad14a23c3ff26e2a0ee161d8a1593b7d642f5e2a93ac)
BibTeX
@misc{dce217f4e5a849,
  title = {SAVIER: Source-Anchored Visual Inspection and Evidence-Guided Repair for Vietnamese Cultural Text-to-Image Generation — arXiv:2611.00722},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00722},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e217f4e5a849; sha256 20df11f17279479cf308ad14a23c3ff26e2a0ee161d8a1593b7d642f5e2a93ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present SAVIER, a training-free, one-pass framework that repairs the depiction of a named Vietnamese cultural entity in a generated image while preserving the scene details requested by the user. The problem is hard because a plausible scene can miss the cues that identify the entity, and prompt-level refinement never inspects the image it produces. SAVIER starts from a Culture-TRIP expanded prompt; a Curator separates source-linked cultural cues from prompt-preservation requirements, a prompt-blind Observer describes the first image, and a Refiner turns the discrepancies into at most three positive instructions before one regeneration with the same seed and a fixed bank of reference photographs. On the 50 bilingual prompts of ViCuP, evaluated with SDXL and FLUX.1-dev against a frozen, human-verified visual contract, SAVIER raises contract fulfillment from 55.6 to 69.6 and from 59.1 to 67.3 over Culture-TRIP and raises CAIRE cultural relevance on FLUX.1-dev. A reference-only ablation that removes the agent repair shows that SAVIER's photographs account for most of the contract gain; the agent roles add country-level relevance on FLUX.1-dev without lowering adherence to the original prompt under the official VQAScore. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00722 — 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 2026-11-03T18:09:53.538Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).