Get Started
Home
Topics
Search
Library
Research questionHow can conditioned diffusion models be guided without score functions when diffusion coefficients are singular and conditional densities are absent or nonsmooth?Score-based guidance becomes difficult when the diffusion coefficient is singular and relevant conditional densities are unavailable or lack smoothness. Conventional density-derived guidance may therefore not be well defined in these processes.
AI
Diffusion Models
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Conditioning Degenerate Diffusion ModelsThe source develops a theoretical construction using causal optimal transport and the predictable representation property of conditioned diffusion processes whose associated martingale problem is well posed. It provides no particular application or empirical benchmark.research paper · Sep 3, 2026
Related questions
How can reinforcement learning post-training for diffusion models avoid objective mismatch and high-variance updates?How can text-to-image diffusion models preserve prompt alignment without the extra sampling cost of classifier-free guidance?How can diffusion-based music generators steer pitch content without retraining or modifying the base model?How should diffusion samplers allocate limited neural evaluations without sacrificing generated image quality?