Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are typically defined on individual samples, for many applications it is desirable to steer according to distribution-level rewards, for example to calibrate with population-level information or to encourage diversity.
arXiv:2606. 02884v1 Announce Type: cross Abstract: Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time.
By Sanjit Dandapanthula, Nicholas M. Boffi
arXiv:2606. 13240v1 Announce Type: cross Abstract: A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance.
By Rapha\"el Razafindralambo, R\'emy Sun, Fr\'ed\'eric Precioso, Jes Frellsen, Pierre-Alexandre Mattei
arXiv:2607. 07693v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences.
By Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay
arXiv:2607. 01144v1 Announce Type: cross Abstract: While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution.
By Binglin Ji, Anindya Sarkar, Hengchang Lu, Jens Sj\"olund, Yevgeniy Vorobeychik
arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.
By Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana
arXiv:2602. 03211v2 Announce Type: replace-cross Abstract: Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent.
By Yeongmin Kim, Donghyeok Shin, Byeonghu Na, Minsang Park, Richard Lee Kim, Il-Chul Moon
arXiv:2507. 08390v5 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training.
By Meihua Dang, Jiaqi Han, Minkai Xu, Kai Xu, Akash Srivastava, Stefano Ermon
arXiv:2608. 03967v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward.
By Yordan Raykov, Rodrigo Veiga
arXiv:2606. 15359v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for planning and control by learning multimodal distributions over actions and trajectories.
By Paolo Giaretta, Zeyang Li, Navid Azizan
arXiv:2510. 11711v3 Announce Type: replace Abstract: This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions.
By Sanghyeok Choi, Sarthak Mittal, V\'ictor Elvira, Jinkyoo Park, Esmeralda S. Whitammer
arXiv:2503. 14549v4 Announce Type: replace Abstract: Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints.
By Michael Chertkov, Hamidreza Behjoo, Sungsoo Ahn