Research
Marimuthu Kalimuthu develops neural operators and neural fields for learning the solutions of partial differential equations. His work combines local and global features to capture fine spatial structure in physical systems, including fluid flows. He also investigates active learning methods that reduce the amount of simulation data needed to train neural solvers.
Selected publications
- LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators 2025
- Active Learning for Neural PDE Solvers 2025
- Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations 2024
Information reviewed 26 September 2026 · University profile