Research
Conditioning Degenerate Diffusion Models
arXiv:2609.04090v1 Announce Type: new Abstract: Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process wit
arXiv:2609.04090v1 Announce Type: new Abstract: Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities either do not exist or are not smooth, we use causal optimal transport to define approximate loss functions that identify a minimum-entropy control for guidance under minimal assumptions. Our approach relies on causal optimal transport and its characterization through the predictable representation property of (conditioned) diffusion processes whose associated martingale problem is well posed, a la Ustunel.
Related
- Supervised Guidance Training for Infinite-Dimensional Diffusion Models
- Spectral Guidance for Flexible and Efficient Control of Diffusion Models
- From Score Approximation to Distribution Approximation in Score-Based Diffusion Models
- Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions
Source: arXiv cs.LG | 2026-09-04