Research Interest
My research interests are in numerical optimization, differential geometry, physics-based simulation in computer graphics, and applying machine learning to solve their systems, including various simulations of deformable solids, fluids, and thermomechanical effects and non-linear/linear optimization for sparse matrices.
Publications
-
A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
-
A Deep Conjugate Direction Method for Iteratively Solving Linear Systems
-
Fiber-Dependent Approach for Fast Dynamic Character Animation
Invited Talks
- Deep Learning Approach to Approximate the Solution for Poisson Matrix. Scientific Computing and Machine Learning (SCML 2024), Kyoto, Japan, March 19–23, 2024. link
- A Deep Conjugate Direction Method for Iteratively Solving Linear Systems. Visual Computing (VC 2023), Tokyo, Japan, September 17–20, 2023. link
Seminars
- 深層学習を用いたポアソン方程式解法の近似アプローチについて RICOS Seminar #1, February 4, 2025. link
Awards
Research Support
- Jan 2020 – Aug 2020 (SGU): Top Global University Project: Waseda Goes Global - A Plan to Build a Worldwide Academic Network. link
- Aug 2019 – Dec 2019 (Ministry of Education, Japan): Tobitate ryugaku Japan project. link
- Jan 2018 – Mar 2018 (SGU): Top Global University Project: Waseda Goes Global - A Plan to Build a Worldwide Academic Network. link
Contact
Email: kintakosu0721[@]gmail.com
Google Scholar: scholar profile
CV: download PDF