D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform

Excerpt

arXiv:2610.04938v1 Announce Type: cross Abstract: We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models with generic rewards. D-DOIT formulates adaptation as sampling from a reward-tilted target distribution and realizes this transport through Doob's h-transform of the discrete diffusion reverse kernel, using only reward values rather than reward gradients. Unlike continuous diffusion, masked discre