{
  "abstract": "Machine learning supports materials design, atomistic simulation and experimental characterization, yet models and workflows remain fragmented. We present PaddleMaterials, an open-source framework integrating heterogeneous materials-learning tasks while preserving task-specific representations and scientific semantics. It unifies data processing, training, evaluation, pretrained-model management and workflows across six task classes: property prediction, structure generation, machine-learning interatomic potentials, electronic-structure fields, spectrum elucidation and microscopy image processing. Task interfaces record physical quantities, units, aggregation conventions and references, making cross-task composition verifiable. A shared compiler backend enables switching from dynamic-graph to compiled execution through one setting, using graph optimization, operator fusion and hardware-targeted code generation without changing model definitions. Across 65 model instances in 11 groups, compiled execution accelerated every instance in eight groups, with group median speedups of 11%-224% and group maximum speedups of 11%-336%. Case studies on LiMnO2 and toluene link structure generation or spectrum elucidation, interatomic-potential relaxation, property prediction and electron-density prediction, using same-geometry density functional theory (DFT) calculations as references. For LiMnO2, predicted formation energies for generated and relaxed structures differed from same-geometry PBE+U references by at most 7 meV per atom, while the computational cost of model steps was less than one-twentieth of a DFT single-point calculation. PaddleMaterials extends unified materials workflows beyond conventional property, potential and structure-generation tasks while supporting verifiable cross-task operations and compiled execution.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03154",
  "author_total": 8,
  "authors": [
    {
      "name": "Xuwei Liu"
    },
    {
      "name": "Zhimin Zhang"
    },
    {
      "name": "Xiaoguang Hu"
    },
    {
      "name": "Zhongwei Liu"
    },
    {
      "name": "Yuanhui Sun"
    },
    {
      "name": "Jun Huo"
    },
    {
      "name": "Hua Wu"
    },
    {
      "name": "Haifeng Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/16kh303tb9zct.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03154",
  "fulltext_url": null,
  "id": "16kh303tb9zct",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03154",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "cs.LG"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03154",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/16kh303tb9zct.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:04Z",
      "native_id": "2611.03154",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03154"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science",
  "title_text": "PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science",
  "type": "preprint",
  "updated_at": "2026-11-03T12:21:04Z",
  "url": "https://research.draconitic.com/paper/16kh303tb9zct",
  "venue": "arXiv",
  "versions": []
}