4 papers
DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
Ziqing Wang, Qijie Zhu, Weimin Wu +4
Scientific design often requires jointly satisfying multiple objectives and constraints. Pretrained masked diffusion models provide a generative foundation for this task, but fine-…
D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
Jieke Wu, Qijie Zhu, Weimin Wu +3
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…
Training-Free Adaptation of Diffusion Models via Doob's -Transform
Qijie Zhu, Zeqi Ye, Han Liu +2
Adaptation methods have been a workhorse for unlocking the transformative power of pre-trained diffusion models in diverse applications. Existing approaches often abstract adaptati…
Provable Separations between Memorization and Generalization in Diffusion Models
Zeqi Ye, Qijie Zhu, Molei Tao +1
Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization -- reproducing training data rather than generating novel outpu…