Obtaining human-interpretable explanations of large, general-purpose language models is an urgent goal for AI safety.

We develop a 3D equivariant diffusion model that jointly learns the generative process of both fragment poses and the 3D structure of the linker.

First,weintroduce canonicalized roto-translated local coordinate frames for interacting dynamical systems formalized in geometric graphs. Second, by operating solely on these coordinate frames, we enable roto-translation invariant edge prediction and roto-translation equivariant trajectory forecasting. Third, we present anovelmethodology for natural anisotropic continuous filters based onrelativelinear and angular positions ofneighboring objects in the canonicalized local coordinate frames.