- Machine Learning Enhanced Approximate Inverse Preconditioners. F. Brarda, T. Xu, R. Li, Y. Xi. In preparation.
- Spectral-Refiner: Fine-Tuning of Accurate Spatiotemporal Neural Operator for Turbulent Flows. S. Cao, F. Brarda, R. Li, Y. Xi. International Conference on Learning Representations (ICLR) 2025. arXiv preprint arXiv:2405.17211.
RESEARCH
Most of my academic journey has been deeply rooted in classical numerical analysis, a field I have grown to appreciate and admire over the years.
During my Ph.D., I have explored cutting-edge research that blends Machine Learning (ML) and Artificial Intelligence (AI) to achieve innovative results.
Attending conferences across the country has broadened my perspective on the transformative role of ML in modern science and its rapid evolution in recent years. My two Summers at Lawrence Livermore National Laboratory (LLNL) allowed me to collaborate with pioneers in computational methods, further inspiring my passion for combining classical analysis with data-driven approaches. Through my talks and publications, some of which you can find below, I aim to highlight the power of this synergy.
Attending conferences across the country has broadened my perspective on the transformative role of ML in modern science and its rapid evolution in recent years. My two Summers at Lawrence Livermore National Laboratory (LLNL) allowed me to collaborate with pioneers in computational methods, further inspiring my passion for combining classical analysis with data-driven approaches. Through my talks and publications, some of which you can find below, I aim to highlight the power of this synergy.
Invited Talks
- Efficient Hybrid Spatial-Temporal Operator Learning. SIAM Student Seminar, GATech, Atlanta, GA. March 29, 2024.
- Development of a Massively Parallel Remeshing Code for Exascale Geometries. MICROCARD Workshop, Bordeaux, France. July 6-7, 2022.
Contributed Talks
- Efficient Hybrid Spatial-Temporal Operator Learning. 2024 SIAM Conference on Mathematics for Data Science. Atlanta, GA, USA. October 21-25, 2024.
- Efficient Hybrid Spatial-Temporal Operator Learning. International Conference On Preconditioning Techniques For Scientific and Industrial Applications. Atlanta, GA, USA. June 10-12, 2024.
- Efficient Hybrid Spatial-Temporal Operator Learning. 18th Copper Mountain Conference on Iterative Methods, Copper Mountain, CO. April 14-19, 2024.
- Numerical Simulation of Pesticide Spray Distribution by UAV for Precision Agriculture. COMSOL Conference 2020 Europe. (held virtually) Grenoble, France. October 14-15, 2020.
Publications