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.
[9] Complex normalizing flows can almost be information Kähler-Ricci flows, 2026, (arXiv)
[8] Pseudo-differential-enhanced physics-informed neural networks, 2026, (arXiv)
[7] Complex variational autoencoders admit Kähler Structure, 2025, submitted, (arXiv)
[6] Inexact calculus of variations on the hyperspherical tangent bundle and its connections to the attention mechanism, 2025, (arXiv)
Note there is a major flaw in this paper. New version to be posted.
[5] Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature, 2025, submitted, (arXiv)
[4] Observability conditions for neural state-space models with eigenvalues and their roots of unity, 2025, to be submitted as a conference paper, (arXiv)
[3] Variational autoencoders with latent high-dimensional steady geometric flows, 2025, in ICNAAM 2025 with Springer Proceedings in Mathematics and Statistics, (arXiv)
[2] Ricci flow regularization in latent spaces for the forward learning of partial differential equations, 2024, presented in SIAM Conference on Applications of Dynamical Systems, (arXiv)
[1] GeONet: a neural operator for learning the Wasserstein geodesic, 2022, with Xiaohui Chen, in UAI 2024,presented in Brown CRUNCH group, (arXiv)