works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

cs.LG2026

Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers

Zhangyong Liang, Huanhuan Gao

Energy natural gradient descent (ENGD) aligns parameter updates with the curvature of an underlying function-space energy, but existing formulations assume an unconstrained Euclide…

cs.LG2026

Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs

Zhangyong Liang, Huanhuan Gao

The paper proposes Disentangled Latent Dynamics Manifold Fusion (DLDMF), a physics‑informed neural framework that separates space, time, and PDE parameters, maps parameters to a co…

cs.LG2026

Interface-Aware Neural Newton Preconditioning for Robust Cohesive Zone Model Simulations

Zhangyong Liang, Huanhuan Gao

Cohesive Zone Models (CZMs) are widely used to simulate interface fracture, delamination, adhesive failure, and fiber--matrix debonding in aerospace composite structures. In implic…

stat.ML2026

Neural Dynamic Data Valuation via Stochastic State-Adjoint Trajectories

Zhangyong Liang, Ji Zhang, Huanhuan Gao

Classical data valuation defines a data point's value through the finite marginal contribution , but estimating this quantity over coalitions requires repeated…

cs.LG2026

Categorical Optimization with Bayesian Anchored Latent Trust Regions for Structural Design under High-Dimensional Uncertainty

Zhangyong Liang, Jie Hou, Huanhuan Gao +1

Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of admissible instances, while ea…

cs.LG2026

Stochastic Dimension Implicit Functional Projections for Global Integral Conservation in High-Dimensional PINNs

Zhangyong Liang, Huanhuan Gao

Enforcing prescribed global integral constraints in mesh-free neural PDE solvers is challenging in high-dimensional domains. Existing projection methods for spatial integrals are o…