{
  "abstract": "No interatomic potential has offered universality across chemistry, near-first-principles accuracy and the speed of empirical potentials at once. Here we introduce DPA4C, an equivariant potential whose architecture and compressed CUDA operators are co-designed under deployment constraints to pursue accuracy and efficiency together. Five variants spanning a 49-fold parameter range form the high-throughput end of the measured accuracy--throughput frontier. The largest variant approaches the accuracy of the MACE-Omat models at about two orders of magnitude higher measured throughput. The most compact reduces the energy, force and stress errors of the fastest existing universal MLIP by 61.4%, 48.1% and 34.3% at 1.92 times its saturated throughput. All five variants complete multimillion-atom simulations on a single GPU and run molecular dynamics for 2.048 billion atoms on 1,024 16-GB NVIDIA V100 GPUs at 83.3--91.2% weak-scaling efficiency. Compared with the MEAM empirical potential, DPA4C-Nano reaches 1.8 and 2.5 times the saturated throughput in single-GPU scans on the same V100 hardware for diamond carbon and FCC copper, respectively. DPA4C therefore brings quantum-trained universal accuracy into a regime of speed and system size previously associated with empirical potentials.",
  "abstract_shown": true,
  "affiliations": [
    "AI for Science Institute , Beijing 100080 , P. R. China",
    "State Key Laboratory of Nuclear Physics and Technology , School of Physics , Peking University , Beijing 100871 , China",
    "HEDPS, CAPT , College of Engineering , Peking University , Beijing 100871 , P. R. China",
    "DP Technology , Beijing 100080 , P. R. China",
    "National Key Laboratory of Computational Physics , Institute of Applied Physics and Computational Mathematics , Fenghao East Road 2 , Beijing 100094 , P. R. China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Tiancheng Li"
    },
    {
      "affs": [
        2,
        1
      ],
      "name": "Jianming Xue",
      "orcid": "0000-0002-0213-9239"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Linfeng Zhang",
      "orcid": "0000-0002-8470-5846"
    },
    {
      "name": "Duo Zhang"
    },
    {
      "affs": [
        2,
        4
      ],
      "name": "Han Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2a8qfrc19w03r.bib",
  "cited_by": 6,
  "doi": "10.48550/arxiv.2608.19041",
  "fulltext_url": null,
  "id": "2a8qfrc19w03r",
  "issns": [
    "2331-8422"
  ],
  "landing_url": "https://arxiv.org/abs/2608.19041",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7203933277",
  "pdf_url": "https://arxiv.org/pdf/2608.19041",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-19",
  "publisher": "Cornell University",
  "ris": "https://research.draconitic.com/paper/2a8qfrc19w03r.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:07Z",
      "native_id": "W7203933277",
      "source": "openalex",
      "url": "https://arxiv.org/abs/2608.19041"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Universal Machine-learning Molecular Dynamics at the Speed of Empirical Potentials",
  "title_text": "Universal Machine-learning Molecular Dynamics at the Speed of Empirical Potentials",
  "type": "preprint",
  "updated_at": "2026-11-08T13:20:57Z",
  "url": "https://research.draconitic.com/paper/2a8qfrc19w03r",
  "venue": "arXiv (Cornell University)",
  "versions": []
}