AI RESEARCH

SURGE: Approximation-free Training Free Particle Filter for Diffusion Surrogate

arXiv CS.LG

ArXi:2605.18745v1 Announce Type: cross Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations,