3 papers
cs.AI2026
When Does AI for PDEs Yield Scientific Evidence?
Wenshuo Wang
Existing AI-for-PDE benchmarks primarily assess models in terms of predictive or approximation accuracy. In physics research, however, AI outputs often serve as evidence for scient…
cs.LG2026
Posterior-First Neural PDE Simulation: Inferring Hidden Problem State from a Single Field
Wenshuo Wang, Fan Zhang
Neural PDE simulators often receive only a single observed field at deployment. In this setting, a field-to-future predictor can collapse distinct latent problem states into the sa…
cs.AI2026
System-Anchored Knee Estimation for Low-Cost Context Window Selection in PDE Forecasting
Wenshuo Wang, Fan Zhang
Autoregressive neural PDE simulators predict the evolution of physical fields one step at a time from a finite history, but low-cost context-window selection for such simulators re…