Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo
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 ne...
Lu-Ran Wang, Lin-Rui Ma, Hannes Stärk et al.
· 0 citations