The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…

The paper reformulates nonreversible perturbations of Fokker--Planck dynamics as gauge fields, providing a unified operator viewpoint to analyze relaxation processes and develop methods for learning o…

The paper proposes PG-RSSNN, a physics-guided recurrent state-space neural network that improves multi-step prediction stability and accuracy compared to both pure black-box and pure physics models, e…

The paper proposes a novel hybrid framework that couples Large Language Models (LLMs) with simplified physics-based simulations to improve the synthesis planning of novel inorganic crystalline materia…

The paper introduces hybrid neural world models that provide fast, multi-horizon predictions for complex physical dynamics, implicitly handling sharp events like shocks and contacts without explicit t…

This review surveys advanced techniques—including generative models, multimodal learning, and closed-loop workflows—for automated inverse materials design, enabling the targeted discovery of novel cry…

The paper introduces an improved PULSE method to efficiently estimate the thermodynamic properties of chemically disordered compounds by sampling and estimating the system's partition function, demons…

The paper proposes using a Physics-Informed Neural Network (PINN) residual as an efficient, physics-guided indicator to guide adaptive mesh refinement (AMR) for classical finite-difference PDE solvers…

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime…

The paper introduces the Kerimov-Alekberli model, an information-geometric framework that uses non-equilibrium thermodynamics and stochastic control to provide a physically grounded method for detecti…

The paper introduces a non-intrusive variant of index-aware learning for solving differential-algebraic equations (DAEs), ensuring that learned solutions maintain physical consistency like Kirchhoff's…

This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…

The paper proposes an Entropy Dynamics framework to analyze the stability and failure modes of centralized orchestration in Multi-Agent Systems, identifying a 'Reasoning Trap' where complex reasoning…

This paper establishes an exact mathematical correspondence between training and inference in deep learning and the solution of Hamilton-Jacobi partial differential equations, unifying multiple theore…

The paper introduces a novel padding method that leverages crystal symmetry to enhance the encoding of complex inorganic structures, significantly improving the generation of stable, novel materials.

The paper introduces an Equilibrium Propagation (EP)-based training method for Predictive Coding Networks (PCNs), successfully training a large-scale VGG10 model on ImageNet and achieving state-of-the…

The paper demonstrates that enforcing a local conservative finite volume structure is crucial for achieving stable, accurate long-term autoregressive rollouts of plasma transport simulations, outperfo…

The authors demonstrate that a physics foundation model, finetuned on simulation data, can successfully predict complex laboratory fluid dynamics, specifically resolving a long-standing discrepancy in…

The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.