{
  "abstract": "Exact stochastic equations for non-equilibrium dynamics are rarely accessible. We show that the long-time evolution of stochastic dynamics can be predicted from configuration pairs at a fixed short time lag, without knowledge of the equation of motion. Generative diffusion models learn the finite-time transition kernel from these pairs, and iterating it propagates the dynamics far beyond the training lag. For two-dimensional Model B, the diffusive dynamics of a conserved order parameter, the learned kernels reproduce dynamic critical scaling and self-similar $t^{1/3}$ coarsening. Agreement with direct simulations persists on lattices twice the largest training size and for initial ensembles absent from training. For driven colloids in a periodic optical potential, ten minutes of measured trajectories suffice to predict the particle current and mean passage time over the next twenty minutes within experimental uncertainty. Short-time observations thus contain the information needed to predict emergent non-equilibrium dynamics at much longer times.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.00546",
  "author_total": 3,
  "authors": [
    {
      "name": "Yang-yang Tan"
    },
    {
      "name": "Jinyang Li"
    },
    {
      "name": "Lingxiao Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7je0kn0ck1rz5.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.00546",
  "fulltext_url": null,
  "id": "7je0kn0ck1rz5",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.00546",
  "language": null,
  "licence": "CC-BY-SA-4.0",
  "licence_label": "CC BY-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.stat-mech"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "hep-lat"
    ],
    [
      "openalex",
      "3104|Theoretical and Computational Physics"
    ]
  ],
  "openalex": "W7216040493",
  "pdf_url": "https://arxiv.org/pdf/2610.00546",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7je0kn0ck1rz5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:03Z",
      "native_id": "2610.00546",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.00546"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:hep-lat",
      "subfield": "high-energy"
    },
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.stat-mech",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Generative Modeling of Stochastic Dynamics for Long-Time Evolution",
  "title_text": "Generative Modeling of Stochastic Dynamics for Long-Time Evolution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:03Z",
  "url": "https://research.draconitic.com/paper/7je0kn0ck1rz5",
  "venue": "arXiv",
  "versions": []
}