Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks
Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks
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 …