Generating Molecular Conformers with Manifold Diffusion Fields

Diffusion probabilistic fashions have rapidly change into a serious method for generative modeling of photographs, 3D geometry, video and different domains. Nonetheless, to adapt diffusion generative modeling to those domains the denoising community must be rigorously designed for every area independently, oftentimes beneath the belief that knowledge lives in an Euclidean grid. On this paper we introduce Diffusion Probabilistic Fields (DPF), a diffusion mannequin that…

See paper particulars