3 papers
cs.LG2026
Full-Spectrum Graph Neural Networks: Expressive and Scalable
Xiaohan Wang, Deyu Bo, Longlong Li +1
It is well established that spectral graph neural networks (GNNs) can universally approximate node signals; however, their expressive power remains bounded by the 1-dimensional Wei…
cs.LG2025
Seeing the Many: Exploring Parameter Distributions Conditioned on Features in Surrogates
Xiaohan Wang, Zhimin Li, Joshua A. Levine +1
Recently, neural surrogate models have emerged as a compelling alternative to traditional simulation workflows. This is accomplished by modeling the underlying function of scientif…
cs.LG2025
Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology
Xiaohan Wang, Matthew Berger
For domains that involve numerical simulation, it can be computationally expensive to run an ensemble of simulations spanning a parameter space of interest to a user. To this end,…