In this paper, we introduce the Radon-Nikodym Estimator (RNE), a flexible, plug-and-play framework for diffusion inference-time density estimation and control, based on the concept of the density ratio between path distributions. RNE connects and unifies a variety of existing density estimation and inference-time control methods under a single and intuitive perspective, stemming from basic variational inference and probabilistic principles therefore offering both theoretical clarity and practical versatility. Experiments demonstrate that RNE achieves promising performances in diffusion density estimation and inference-time control tasks, including annealing, composition of diffusion models, and reward-tilting.
View on arXiv@article{he2025_2506.05668,
title={ RNE: a plug-and-play framework for diffusion density estimation and inference-time control },
author={ Jiajun He and José Miguel Hernández-Lobato and Yuanqi Du and Francisco Vargas },
journal={arXiv preprint arXiv:2506.05668},
year={ 2025 }
}