Author

Si-Ming Liang

h-index 5 View on Semantic Scholar

We have 3 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

From Variational Optimization to Flow-Based Transport: Posterior-Geometry Regularization for Ill-Conditioned Data Assimilation

Variational data assimilation computes a Bayesian update through optimization on a fixed posterior geometry, whose conditioning is determined by the prior covariance and the observation operator. In strongly anisotropic, weakly observed, or highly informative regimes, this geometry can become severely ill conditioned,...

Si-Ming Liang, Feng Bao, Hristo G. Chipilski et al. · 0 citations

#generative ai Preprint Sep 2026

Score-Based Generative Data Assimilation for Integrating Aggregated Surveillance Data into Agent-Based Models in Epidemic Tracking

A generative AI-based data-assimilation framework for partially observed epidemic ABMs that estimates both the epidemic state and a heterogeneous parameter field while respecting the gap between observable macrostates and latent agent-level microstates is developed.

Si-Ming Liang, Jacob Hauck, Ming-Lei Yang et al. · 0 citations

#artificial intelligence Apr 2026

Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Earth System Prediction

STORM is introduced, a one-stage generative AI framework that reformulates DA as diffusion-based Bayesian posterior sampling, replacing online PDE ensemble forecasts with scalable AI inference, enabling high-resolution, long-context Earth modeling and demonstrating improved accuracy.

Xiao Wang, Ze-Zhong Zhang, Isaac Lyngaas et al. · arXiv.org · 1 citation