structure-preserving

This paper proposes Structure-Preserving Epistemic Neural Networks (S-PENNs), a framework for uncertainty quantification in scientific machine learning models with hard architectural constraints, instantiated for GENERIC dynamics to ensure thermodynamically consistent rollouts and calibrated prediction intervals with reduced computational cost.

The paper introduces CoSynFlow, a conformal symplectic neural flow that learns continuous-time solution maps for dissipative Hamiltonian dynamics while preserving the conformal symplectic structure and enabling cross-system prediction without retraining.

This paper introduces Latent Lie-Poisson Neural Networks (LLPNNs), a structure-preserving framework for learning Lie-Poisson dynamics directly from observable data, using geometric methods and Magnus-based Lie-group updates. It demonstrates strong accuracy and robustness on rigid body, underwater vehicle, and optimal control examples.

This paper presents a multi-stage LLM pipeline for structure-preserving Marathi-to-English translation of government documents, integrating layout-aware OCR and HTML reconstruction to maintain formatting and domain terminology.

This paper proposes structure-preserving neural surrogates for partial differential equations that integrate Gaussian process regression to provide tractable uncertainty quantification, enabling real-time simulation with closed-form error estimates.