Runzhong Wang

Expressive Power of Subgraph Graph Neural Networks for Graphs with Bounded Cycles

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning

Batched Bayesian optimization with correlated candidate uncertainties