Metraipolis › archive › dc_64d4d07d2264
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation — arXiv:2610.11067
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11067
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:16.239Z
- SHA-256 of the archived text
88de35e460f2f48d0d7a2c9327a484a31285129e620aefc8a0cb5c409770aef4- Stable URL of this page
https://metraipolis.com/documento/dc_64d4d07d2264
How to cite
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation — arXiv:2610.11067 — arXiv (en), https://arxiv.org/abs/2610.11067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64d4d07d2264 (Metraipolis archive dc_64d4d07d2264, sha256 88de35e460f2f48d0d7a2c9327a484a31285129e620aefc8a0cb5c409770aef4)
BibTeX
@misc{dc64d4d07d2264,
title = {Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation — arXiv:2610.11067},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11067},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64d4d07d2264; sha256 88de35e460f2f48d0d7a2c9327a484a31285129e620aefc8a0cb5c409770aef4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classes, domains, or compositions of tasks. In this paper, we introduce a Diffusion Meta-Prompt (DMP) model , a framework that models the distribution of learned prompts using diffusion models. Given a repository of previously learned prompts, DMP is trained and sampled without access to the original task examples or task losses, and synthesizes new prompts conditioned on natural language task descriptions. To improve the sampling stability, we introduce a test-time steering strategy for DMP, which uses the best training-selected prompt in the repository as a latent anchor during diffusion sampling, without retraining the DMP or accessing test classes. DMP improves generalization across classification, retrieval and text-to-image generation tasks, supports concept composition and negative prompting without explicit training. It reduces storage and inference costs by over 90% compared to prompt retrieval methods. For composite classification, DMP achieves upto 2.0% average gain over prior meta-learning methods across 55 pairs of datasets with gains as high as 8.5% on specific pairs such as Eurosat and Flowers. DMP also enhances cross-task generalization with ~2-9% improvement for hierarchical classification task. We further provide a theoretical guarantee bounding the expected task loss of prompts sampled from a DMP. Code is available: this https URL Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.11067 — 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 2026-10-09T05:55:07.092Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).