Research
A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models
arXiv:2608.19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an u
arXiv:2608.19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term. The plug-in term separates the conditioning contribution from the learned unconditional dynamics, offering a transparent view of how the condition steers generation of the target distribution. Building on this, we derive explicit conditional reverse-time SDEs and approximate probability-flow ODEs, enabling principled and directly comparable conditional samplers. To reduce the induced ODE--SDE discrepancy, we introduce a log-Fokker--Planck residual regularization that improves ODE sampling quality. Experiments on conditional image generation tasks demonstrate competitive performance and support the effectiveness of the plug-in conditioning view. Additional ODE--SDE comparison experiments show that the log-Fokker--Planck residual regularization improves deterministic ODE sampling.
Related
- DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
- Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models
- Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA
- EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
- eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models
Source: arXiv cs.CV | 2026-08-21