Metraipolis › archive › dc_72cf352c3dd4
Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models — arXiv:2610.18990
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.18990
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:11.502Z
- SHA-256 of the archived text
2f7d67609b56e236e0397d10d211af944241eb1859693f154423487e7da037b5- Stable URL of this page
https://metraipolis.com/documento/dc_72cf352c3dd4
How to cite
Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models — arXiv:2610.18990 — arXiv (en), https://arxiv.org/abs/2610.18990 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72cf352c3dd4 (Metraipolis archive dc_72cf352c3dd4, sha256 2f7d67609b56e236e0397d10d211af944241eb1859693f154423487e7da037b5)
BibTeX
@misc{dc72cf352c3dd4,
title = {Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models — arXiv:2610.18990},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.18990},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72cf352c3dd4; sha256 2f7d67609b56e236e0397d10d211af944241eb1859693f154423487e7da037b5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.18990. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Low-Rank Adaptation (LoRA) has made diffusion model personalization affordable and widely shareable, but it also creates moderation risks when harmful or problematic content is not faithfully disclosed. Hence, it is desired to develop a mechanism that, given a LoRA adapter, discovers the concept it was trained to generate, so as to support downstream investigation. We characterize the target concept through the conditioning input that most clearly exposes what the LoRA has learned. Such an input should induce coherent LoRA outputs that are distinctive from those of the base model and strongly align with the learned LoRA subspace. We therefore formulate concept discovery as searching for the conditioning input that jointly maximizes output coherence, LoRA-induced distinctiveness, and subspace alignment. Even with a clear objective, however, optimizing it over an open-ended input space is prohibitively expensive, since reliable evaluation of coherence and distinctiveness requires repeated diffusion rendering. Crucially, we observe that an input need not be rendered to determine whether it is promising. Its alignment with the learned LoRA subspace provides a lightweight signal for localizing promising candidates before visual verification. Based on this insight, we develop a two-stage framework for text-to-image LoRAs. Subspace-Guided Evolutionary Search (SGES) uses render-free subspace alignment to explore candidate prompts and retain a compact shortlist, while Paired Visual Identification (PVI) renders only these candidates and compares the LoRA and base-model outputs to identify those exhibiting coherent and distinctive generation behavior. This design enables efficient and reliable discovery of previously unknown concepts encoded in LoRA adapters. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.18990 — 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 2026-10-15T13:53:35.815Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).