Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks

arXiv:2403.15441v1 Announce Type: cross
Abstract: Advanced generative model (e.g., diffusion model) derived from simplified continuity assumptions of data distribution, though showing promising progress, has been difficult to apply directly to geometry generation applications due to the multi-modality and noise-sensitive nature of molecule geometry. This work introduces Geometric Bayesian Flow Networks (GeoBFN), which naturally fits molecule geometry by modeling diverse modalities in the differentiable parameter space of distributions. GeoBFN maintains the SE-(3) invariant density modeling property by incorporating equivariant inter-dependency modeling …

abstract advanced applications apply arxiv assumptions bayesian continuity cs.ai cs.lg data diffusion diffusion model distribution flow generative generative modeling geometry modeling molecules nature networks noise physics.chem-ph progress q-bio.bm simplified type via work