Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models 事件

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models 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. This paper studies an efficient test-time scaling method for sampling from regions with higher human-aligned reward values. Existing methods for computing the expected future reward (EFR) face important limitations: backward rol