Tag: bon

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis arXiv:2507.05913v1 Announce Type: new Abstract: A simple yet effective method for inference-time alignment of generative models is Best-of-$N$ (BoN), where $N$ outcomes are sampled from a reference policy, evaluated using a proxy reward model, and the highest-scoring one is selected. While prior work argues that…