DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design

Excerpt

arXiv:2610.05808v1 Announce Type: new Abstract: Scientific design often requires jointly satisfying multiple objectives and constraints. Pretrained masked diffusion models provide a generative foundation for this task, but fine-tuning them to meet these objectives and constraints incurs additional training costs, motivating inference-time guidance with frozen models. However, such guidance faces two challenges: pass-or-fail constraints and black-box reward models may provide no useful gradients,