Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering

Excerpt

arXiv:2610.04171v1 Announce Type: cross Abstract: Inference-time steering combines pretrained diffusion experts or rewards without retraining by changing the dynamics that transport noise to data. Feynman-Kac correction compensates for proposal mismatch through importance-weighted sequential Monte Carlo (SMC), whose finite-particle behavior depends on the proposal. Variance-controlling guidance (VCG) improves that proposal by fitting a linear drift correction to minimize empirical log-weight-rat