Metraipolis › archive › dc_31269fc19489
Best-of-$N$ Guidance for Test-time Diffusion Alignment — arXiv:2610.05108
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05108
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:41.665Z
- SHA-256 of the archived text
6a86d2e6b34c026172044388d92e14610b11a62de5a79e66c8d77db87d202ebf- Stable URL of this page
https://metraipolis.com/documento/dc_31269fc19489
How to cite
Best-of-$N$ Guidance for Test-time Diffusion Alignment — arXiv:2610.05108 — arXiv, https://arxiv.org/abs/2610.05108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31269fc19489 (Metraipolis archive dc_31269fc19489, sha256 6a86d2e6b34c026172044388d92e14610b11a62de5a79e66c8d77db87d202ebf)
BibTeX
@misc{dc31269fc19489,
title = {Best-of-$N$ Guidance for Test-time Diffusion Alignment — arXiv:2610.05108},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05108},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31269fc19489; sha256 6a86d2e6b34c026172044388d92e14610b11a62de5a79e66c8d77db87d202ebf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple yet effective algorithm for test-time alignment is Best-of-$N$ (BoN) sampling, which draws $N$ i.i.d. samples from a pre-trained diffusion model and outputs the single highest-reward sample. Despite its empirical success, BoN makes limited use of reward information, as it is incorporated only at the final selection stage without influencing the reverse diffusion trajectory during sampling. Consequently, BoN sampling does not improve the average alignment of generated samples and is primarily suited to single-output settings. We propose Best-of-$N$ Guidance (BoNG), a novel method that integrates the principle of BoN sampling directly into the reverse diffusion process. BoNG performs online BoN selection over denoising particles and adjusts the reverse diffusion process to steer the particle population toward higher-reward regions during generation. Specifically, by introducing an asymmetric guidance interaction among denoising particles, BoNG uses the current BoN particle as a guidance signal to the rest of the particle population. This particle-level interaction reshapes the sampling process toward higher-reward regions, enabling BoNG to improve not only the final best sample beyond Vanilla BoN sampling, but also the average quality of generated samples. Over 36 empirical comparisons, BoNG achieves the best performance in 29 cases, ranking first in 80.56% of the comparisons against SMC and Vanilla BoN sampling. BoNG also supports multi-output capability, achieving 1.3$\times$ ImageReward score of the latest sample-based guidance method with a 1.6$\times$ speedup. We release the code at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.05108 — 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 2026-10-06T05:24:05.971Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).