D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
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 di...
Jie-Ke Wu, Qi-Jie Zhu, Wei-Min Wu et al.
· 0 citations