🏢 University of Notre Dame

Masked hard-attention transformers, with strict masking, precisely capture star-free languages, matching the expressive power of linear temporal logic.

Graph Diffusion Transformer (Graph DiT) masters multi-conditional molecular generation by cleverly integrating property representations into a graph-dependent noise model, achieving superior performan…

GFT: a novel graph foundation model using transferable computation trees as tokens, improving generalization and reducing negative transfer in graph learning.