Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo

Excerpt

arXiv:2610.00395v1 Announce Type: new Abstract: Inference-time steering enables pretrained diffusion models to satisfy new constraints without full retraining. However, specificity-aware generation is difficult: repelling samples from a negative reference distribution can also erode the positive distribution where the two overlap. The key challenge is to suppress negative mass while minimally distorting the positive distribution. We address this problem by formulating specificity-aware steering