arXiv subjects

Yong-Bin Zhuang

Publications and source records attributed to Yong-Bin Zhuang.

5 recordsLinked to original sources

arXiv2026

Ai2-Kit: Streamlining AI-Accelerated Ab Initio Workflows for Complex Chemical Systems

Molecular simulations of complex chemical systems, such as catalysis, electrochemistry, and energy storage, often need to capture the interplay of effects such as electronic structure, finite-temperature fluctuations, and electric-field response. Such complexity is difficult to address with traditional ab initio calculations, which are limited by the time and length scales they can reach. AI-accelerated ab initio (AI2) methods use machine learning potentials trained on first-principles data to replace expensive electronic-structure calculations, extending ab initio accuracy to these regimes, but their routine application requires reliable workflows that connect first-principles calculations, model training, molecular dynamics, enhanced sampling, trajectory analysis, and HPC orchestration. Here we present ai2-kit, a software toolkit for developing accessible, reproducible, and extensible AI2 workflows. ai2-kit provides high-semantic-density command-line interfaces and Python APIs for structure and dataset conversion, batch task generation, active-learning screening, job orchestration, and workflow recovery. We demonstrate ai2-kit in four representative applications: active-learning-based machine learning potential construction, free-energy perturbation for redox and acid-base processes, electrochemical machine learning potentials for electrified interfaces, and spectroscopies from machine learning molecular dynamics. ai2-kit also provides AI-agent skills that help users adapt these use cases into customized workflows for their own chemical systems and computational software stacks. Together, ai2-kit helps turn AI2 methods from bespoke computational protocols into reusable and extensible workflows for complex chemical systems, from model construction to property prediction.

physics.chem-ph↗

arXiv2026

Matlantis-PFP v8: Universal Machine Learning Interatomic Potential with Better Experimental Agreements via r2SCAN Functional

Universal Machine Learning Interatomic Potentials (uMLIPs) enable atomistic simulations and high-throughput screening at scales far beyond those accessible with density functional theory (DFT). However, most existing uMLIPs are trained on Perdew--Burke--Ernzerhof (PBE) generalized gradient approximation (GGA) data and are therefore fundamentally limited by PBE-level accuracy. In this paper, we argue that better zero-shot predictions versus experiments must be an explicit design target for uMLIPs and present PFP v8, a uMLIP available on the Matlantis service that overcomes the inherent limitations of the PBE functional by being trained to reproduce the regularized-restored strongly constrained and appropriately normed (r2SCAN) meta-GGA potential-energy surface across a wide range of chemical domains. Without requiring domain-specific fine-tuning, PFP v8 delivers systematically improved agreement with experimental data or high-accuracy references for crystals, molecules, and surfaces, outperforming PBE-based DFT calculations. Crucially, in long-time molecular dynamics simulations that are computationally impractical with DFT, PFP v8 predicts melting points with an average error of approximately 130 K, halving the error relative to PBE-trained models. These results establish that uMLIPs can move beyond the limitations of their training approximations and achieve substantially improved agreement with experiment across diverse chemical domains, further narrowing the gap between simulation and reality.

physics.chem-ph↗

arXiv2025

P-DRUM: Post-hoc Descriptor-based Residual Uncertainty Modeling for Machine Learning Potentials

Ensemble method is considered the gold standard for uncertainty quantification (UQ) in machine learning interatomic potentials (MLIPs). However, their high computational cost can limit its practicality. Alternative techniques, such as Monte Carlo dropout and deep kernel learning, have been proposed to improve computational efficiency; however, some of these methods cannot be applied to already trained models and may affect the prediction accuracy. In this paper, we propose a simple and efficient post-hoc framework for UQ that leverages the descriptor of a trained graph neural network potential to estimate residual errors. We refer to this method as post-hoc descriptor-based residual uncertainty modeling (P-DRUM). P-DRUM models the discrepancy between MLIP predictions and ground truth values, allowing these residuals to act as proxies for prediction uncertainty. We explore multiple variants of P-DRUM and benchmark them against established UQ methods, evaluating both their effectiveness and limitations.

cs.LG↗

arXiv2025

LightPFP: A Lightweight Route to Ab Initio Accuracy at Scale

Atomistic simulation methods have evolved through successive computational levels, each building upon more fundamental approaches: from quantum mechanics to density functional theory (DFT), and subsequently, to machine learning interatomic potentials (MLIPs). While universal MLIPs (u-MLIPs) offer broad transferability, their computational overhead limits large-scale applications. Task-specific MLIPs (ts-MLIPs) achieve superior efficiency but require prohibitively expensive DFT data generation for each material system. In this paper, we propose LightPFP, a data-efficient knowledge distillation framework. Instead of using costly DFT calculations, LightPFP generates a distilled ts-MLIP by leveraging u-MLIP to generate high-quality training data tailored for specific materials and utilizing a pre-trained light-weight MLIP to further enhance data efficiency. Across a broad spectrum of materials, including solid-state electrolytes, high-entropy alloys, and reactive ionic systems, LightPFP delivers three orders of magnitude faster model development than conventional DFT-based methods, while maintaining accuracy on par with first-principles predictions. Moreover, the distilled ts-MLIPs further sustain the computational efficiency essential for large-scale molecular dynamics, achieving 1-2 orders of magnitude faster inference than u-MLIPs. The framework further enables efficient precision transfer learning, where systematic errors from the u-MLIP can be corrected using as few as 10 high-accuracy DFT data points, as demonstrated for MgO melting point prediction. This u-MLIP-driven distillation approach enables rapid development of high-fidelity, efficient MLIPs for materials science applications.

cond-mat.mtrl-sci↗

arXiv2025

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research.

physics.chem-ph↗