arXiv subjects

Taoyuze Lv

Publications and source records attributed to Taoyuze Lv.

5 recordsLinked to original sources

arXiv2026

Neural-Network Solutions to Real-Space Charge Density and Generalization

The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system, such that all GS observables can be expressed as functionals of the GS charge density. Conventional Kohn-Sham density functional theory requires iterative solution of the self-consistent-field equations at substantial computational cost, motivating the development of deep learning surrogates for electronic structure calculations and, in turn, accelerating computer-aided materials design. Here, we propose \textbf{AIDEN}, an \underline{A}tomic-\underline{I}nteraction \underline{D}ensity \underline{E}quivariant \underline{N}etwork for solving real-space charge density. AIDEN separates the element-dependent one-center density from environment-induced density redistribution and represents the latter through complementary atom- and edge-centered tensor correlations. A continuous low-rank Gaussian decoder then reconstructs the density at arbitrary spatial coordinates while reusing atomic encodings independently of the evaluation grid. AIDEN achieves state-of-the-art accuracy on periodic crystal benchmarks while remaining competitive for molecular systems, and further demonstrates zero-shot transferability across several structurally distinct out-of-distribution case studies. Furthermore, AIDEN provides substantially faster inference than both baseline models and full SCF calculations, enabling efficient charge density reconstruction for large-scale electronic structure calculations.

cond-mat.mtrl-sci↗

arXiv2026

Data-model Coevolution as the Architectural Principle for AI-Native Materials Databases

AI-native approaches are reshaping computational materials discovery into iterative data-model coevolution cycles. However, most existing materials databases remain fundamentally data-centric, where predictive models remain external to database state and data growth is decoupled from model updating. Here we formalize data-model coevolution as the architectural basis of AI-native materials databases, where data and predictive models evolve through endogenous generation-evaluation-refinement cycles. Using the Li-P-S ternary as a demonstrative prototype, we generated approximately 70,000 candidate structures, more than 10,000 of which satisfy the stable-unique-novel (S.U.N.) criterion, achieving rapid saturation of local chemical environments together with stabilization of energy distributions. We autonomously found chemically plausible phases and motifs outside the Materials Project (MP) and Alexandria databases, including a stable Li$_2$PS$_3$ phase, the (PS$_3$)$_3^{3-}$ trimer, the (P$_3$S$_8$)$^{3-}$ ring, two isomers of the (P$_2$S$_8$)$^{2-}$ ring, and polymeric (PS$_4$)$_n^{n-}$ chains. Within two to three iterations, the integrated predictive models converged to high precision under a low first-principles cost, and the resulting data-model state can be directly queried for atomistic and electronic-structure properties within the same unified framework. Data-model states can be reused and extended across related chemical systems, enabling scalable and continuous accumulation of computational materials knowledge. These results demonstrate data-model coevolution as a practical architectural principle for AI-era materials data infrastructure.

cond-mat.mtrl-sci↗

arXiv2026

AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials

Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to property prediction. Existing science benchmarks mainly focus on perceptual or knowledge-based tasks, largely ignoring the modelling tasks, a fundamental starting point for any real scientific research. For materials science, constructing and manipulating atomic structures is one of the most creative and least automated steps. In this work, we introduce AtomWorld, a benchmark designed to evaluate the abilities of LLMs on structure modifications. The benchmark includes ten fundamental actions under four widely used modelling categories, enabling verifiable evaluation metrics. We find that Claude Opus 4.6 generally performs the best. While the success rate decreases markedly with increasing modelling complexity, with particularly low success rates (below 12\% for rotation) for operations involving complex spatial relations. Our results suggest that contemporary LLMs are better suited as copilots for materials structure modelling rather than fully unsupervised autonomous scientific agents. Beyond evaluation, AtomWorld also serves as a testbed and playground for developing future structure-aware models, including reinforcement learning and agentic approaches.

cond-mat.mtrl-sci↗

arXiv2025

EAC-Net: Predicting real-space charge density via equivariant atomic contributions

Charge density is central to density functional theory (DFT), as it fully defines the ground-state properties of a material system. Obtaining it with high accuracy is a computational bottleneck. Existing machine learning models are constrained by trade-offs among accuracy, efficiency, and generalization. Here, we introduce the Equivariant Atomic Contribution Network (EAC-Net), which couples atoms and grids to integrate the strengths of grid-based and basis-function frameworks. EAC-Net achieves high accuracy (typically below 1% error), enhanced efficiency, and strong generalization across complex systems. Building on this framework, we develop EAC-mp, a universal charge density model covering the periodic table. The model demonstrates robust zero-shot performance across diverse systems, and generalizes beyond the training distribution, supporting downstream applications such as band structure calculations. By linking local chemical environments to charge densities, EAC-Net provides a scalable framework for accelerating electronic structure prediction and enabling high-throughput materials discovery.

cond-mat.mtrl-sci↗

arXiv2023

Deep Charge: A Deep Learning Model of Electron Density from One-Shot Density Functional Theory Calculation

Electron charge density is a fundamental physical quantity, determining various properties of matter. In this study, we have proposed a deep-learning model for accurate charge density prediction. Our model naturally preserves physical symmetries and can be effectively trained from one-shot density functional theory calculation toward high accuracy. It captures detailed atomic environment information, ensuring accurate predictions of charge density across bulk, surface, molecules, and amorphous structures. This implementation exhibits excellent scalability and provides efficient analyses of material properties in large-scale condensed matter systems.

cond-mat.mtrl-sci↗