We present a principled recipe for building graph foundation models that generalize across arbitrary graphs, features, and label spaces.

We learn non-gradient field dynamics by solving Schrödinger Bridge problem with non-zero reference process drift

we train transferable normalizing flows to sample from peptide Boltzmann distributions up to 8 residues

We propose a diffusion-based approach to sampling from Boltzmann densities based on temperature annealing.

We show the effects of vanishing gradients on GNNs.

We formalize the over-squashing phenomenon in spatiotemporal graph neural networks and analyze how it affects information propagation across the spatial and temporal dimensions.