Paper pages
/papers/functional-flow-matching
Discretization and Statistical Consistency of Functional Flow Matching
When finite sensor implementations converge to a function-space probability flow, separating sensing, operator realization, statistical learning, and numerical error.
/papers/semigroup-consistency
Semigroup Consistency as a Diagnostic for Learned Physics Simulators
A model-agnostic test of whether learned time evolution composes like an autonomous physical flow.
/papers/diagnosing-failure-modes
Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families
A cross-equation study of where neural-operator accuracy breaks and which diagnostics expose the failure.
/papers/cellular-sheaf-neural-operators
Cellular Sheaf Neural Operators for Structure-Preserving Surrogate Modeling of Constrained PDEs
A discretization-aware operator framework built on oriented cell complexes and learned restriction maps.