Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
Neural predictors can be made dynamically feasible without ground-truth controls by a frozen, post-hoc operator that enforces learned dynamics manifolds via iterative control correction.
A novel initialization layer enables GNNs to adaptively transfer across urban environments, achieving superior performance with significantly reduced training times.
The 1-block STGCN variant achieves superior performance with significantly lower computational costs, challenging the assumption that deeper architectures are always better for traffic prediction.
