Search papers, labs, and topics across Lattice.
This paper introduces a novel conditioning mechanism for score-based diffusion models that utilizes multi-speed joint diffusion of both the target and the conditioning input. By implementing a plug-in correction term, the authors achieve a clearer understanding of how conditioning influences the generation process, while also deriving explicit conditional reverse-time stochastic differential equations (SDEs) and probability-flow ordinary differential equations (ODEs). Experimental results on conditional image generation tasks reveal that this approach not only enhances performance but also mitigates discrepancies between ODE and SDE sampling through log-Fokker鈥揚lanck residual regularization.
Conditioning in score-based diffusion models can be transparently managed with a plug-in correction, leading to improved sampling quality and performance in image generation tasks.
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.
