Parallel Tempering Initial Sampling in Inference-Time Reward Alignment 事件

Parallel Tempering Initial Sampling in Inference-Time Reward Alignment arXiv:2605.30991v1 Announce Type: cross Abstract: Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Recently, Sequential Monte Carlo (SMC) has emerged as a powerful framework for this task by iteratively filtering and propagating multiple particles. However, we show that standard SMC-based methods often suffer from poor performan