NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:4132
Title:Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules

This paper introduces a generative model for 3D representations of small molecules, which takes care to encode known symmetries in the energy functions of such molecules. The architecture is novel if a bit on the incremental side, but the application and baseline evaluations are sensible.