One step further with Monte-Carlo sampler to guide diffusion better
arXiv:2603.06685v1 Announce Type: new Abstract: Stochastic differential equation (SDE)-based generative models have achieved substantial progress in conditional generation via training-free differentiable loss-guided approaches. However, existing …
Minsi Ren, Wenhao Deng, Ruiqi Feng, Tailin Wu
조회수 40회