Metraipolis › archive › dc_db121150ee22
Training-Free VLM Personalization via Calibrated Residual Decoding — arXiv:2608.22263
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22263
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:42:42.135Z
- SHA-256 of the archived text
fc95cfd704c9822927f13843e204263f1f77dff7be7039beeb6445fa96b4ac8c- Stable URL of this page
https://metraipolis.com/documento/dc_db121150ee22
How to cite
Training-Free VLM Personalization via Calibrated Residual Decoding — arXiv:2608.22263 — arXiv (en), https://arxiv.org/abs/2608.22263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db121150ee22 (Metraipolis archive dc_db121150ee22, sha256 fc95cfd704c9822927f13843e204263f1f77dff7be7039beeb6445fa96b4ac8c)
BibTeX
@misc{dcdb121150ee22,
title = {Training-Free VLM Personalization via Calibrated Residual Decoding — arXiv:2608.22263},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22263},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db121150ee22; sha256 fc95cfd704c9822927f13843e204263f1f77dff7be7039beeb6445fa96b4ac8c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language models can be personalized in a training-free manner by directly providing user profiles, preferences, or visual references at inference time, without updating model parameters. However, direct personalized prompting does not guarantee that the model will reliably exploit such evidence. The predictive distribution under the positive user profile often mixes two sources: personalized signals genuinely supported by the current profile, and the model's generic visual or linguistic priors. As a result, from the positive-profile response alone, it is difficult to determine whether a high-confidence answer is supported by the user profile or merely reflects the model's default preference. To address this problem, we propose a training-free calibrated residual decoding framework. Given the same image and question, we construct three evidence conditions: a positive profile , a counterfactual profile , and an empty profile . Our method keeps the prediction under as the anchored base, and explicitly estimates the marginal contribution of personalization from score differences across the three conditions. We further introduce normalized-entropy-based uncertainty calibration, allowing the strength of personalized enhancement to adapt to the reliability of the residual signal. Experiments on MMPB, YoLLaVA, and MyVLM show that the proposed method improves personalized multimodal understanding without fine-tuning, with consistent gains on identity-sensitive visual personalization tasks. Additional analysis shows that entropy calibration stabilizes residual decoding when the contrastive personalization signal is uncertain. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22263 — 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 2026-10-18T07:37:52.863Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).