Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models

ArXi:2505.16474v2 Announce Type: replace Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample diversity, predictive learning entails different sources of stochasticity and requires sampling consistency aligned with the ground-truth trajectory, which is a limitation we empirically observe in diffusion models.