Metraipolis › archive › dc_f3586b9388cb

RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models — arXiv:2608.14226

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14226
License (as archived)
CC0-1.0
Archived
2026-10-19T04:04:27.038Z
SHA-256 of the archived text
0f1ce776e39dc57043333c6ccb0bd42b056485d9b2d58805a51758a8b7e3b96b
Stable URL of this page
https://metraipolis.com/documento/dc_f3586b9388cb

How to cite

RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models — arXiv:2608.14226 — arXiv (en), https://arxiv.org/abs/2608.14226 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3586b9388cb (Metraipolis archive dc_f3586b9388cb, sha256 0f1ce776e39dc57043333c6ccb0bd42b056485d9b2d58805a51758a8b7e3b96b)
BibTeX
@misc{dcf3586b9388cb,
  title = {RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models — arXiv:2608.14226},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14226},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3586b9388cb; sha256 0f1ce776e39dc57043333c6ccb0bd42b056485d9b2d58805a51758a8b7e3b96b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14226. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in text-to-image (T2I) models have revolutionized the field of image generation and editing. However, identifying semantics that a T2I model can successfully edit in an image continues to be a challenging task. Most existing approaches require users to manually specify semantics to modify a particular image, a time-consuming process that often involves extensive trial and error. In this paper, we present RankT2I, a novel, training-free, and model-agnostic framework that automates the discovery of editable semantics in diffusion and FLUX-based models. Given a visual domain, we first utilize a multimodal vision-language model to gather a broad set of candidate semantics. We then frame semantic discovery as a set selection problem and use a submodular objective to identify semantics that are relevant, editable, and diverse. Our method helps users efficiently identify a wide range of semantics for text-to-image editing models across several domains while outperforming existing methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.14226 — 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 2026-10-19T03:57:57.943Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).