Search papers, labs, and topics across Lattice.
Email:
3
0
4
0
Integrating physics directly into neural operators can cut prediction errors by up to 2.2 times, transforming how we model complex dynamical systems.
MuRFiV achieves unprecedented long-term prediction accuracy in spatiotemporal dynamics by merging finite-volume principles with deep learning, outperforming conventional neural networks.
D-Flow SGLD unlocks scalable posterior sampling for scientific inverse problems using Flow Matching, achieving a better trade-off between measurement assimilation, posterior diversity, and physics fidelity than existing methods.
