Please also see Google Scholar for my work. I care about the quality of my research. If you spot any (major) errors, please do not hesitate to reach out.
.
Complex variational autoencoders admit Kähler structure, arXiv.
.
Foundations of continuity equations for their neural applications, link. Reading course notes with Rongjie Lai.
.
The calculus of variations of the Transformer on the hyperspherical tangent bundle, arXiv. Preprint / informational manuscript.
.
Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature, arXiv. To be submitted to be determined.
.
Observability conditions for neural state-space models with eigenvalues and their roots of unity, arXiv. To be submitted to a control journal (extended page limit).
.
Variational autoencoders with latent high-dimensional steady geometric flows for dynamics, arXiv. In International Conference of Numerical Analysis and Applied Mathematics (ICNAAM) 2025.
.
Ricci flow regularization in latent spaces for the forward learning of partial differential equations, arXiv. In SIAM Conference of Applications of Dynamical Systems (DS25) 2025.
.
GeONet: a neural operator for learning the Wasserstein geodesic, with Xiaohui Chen, arXiv. In Conference on Uncertainty in Artificial Intelligence (UAI) 2024.
.
.
.
.
.
.