{
  "abstract": "Full-length RNAs, particularly messenger RNAs, often exceed the context lengths used to pretrain existing RNA foundation models, limiting complete-transcript modeling at single-nucleotide resolution. We present RIBOSPAN, a 1.61-billion-parameter bidirectional RNA foundation model natively pretrained with context lengths up to 10,240 nt. RIBOSPAN combines dense bidirectional self-attention, single-nucleotide tokenization, and attention-isolated sequence packing to enable high-resolution modeling of complete long RNAs. Native 10K pretraining preserves strong reconstruction at 10,240 tokens and, in a controlled long-context benchmark, maintains strong contextual responsiveness and context-specific representation separation while keeping perturbation-induced changes highly localized. Inference-time YaRN scaling recovers much of the contextual organization lost by direct short-context extrapolation, but induces substantially greater distal representation diffusion. Frozen RNA-type evaluations show that RIBOSPAN learns state-of-the-art RNA representations, with a particularly clear advantage on long RNAs. Across downstream biological benchmarks, RIBOSPAN emerges as the strongest encoder-only RNA foundation model, achieving state-of-the-art performance in both full-transcript biological property prediction and zero-shot mutation-fitness modeling. Building on the same backbone, we develop a multidimensionally conditioned discrete-diffusion framework for full-length mRNA generation and redesign, including synonymous-codon diffusion for protein-preserving CDS optimization. Together, RIBOSPAN establishes a powerful long-context foundation for transferable RNA representation learning, biological prediction, and full-transcript mRNA design.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.22849",
  "author_total": 5,
  "authors": [
    {
      "name": "Ziyuan Wang"
    },
    {
      "name": "Bohao Tang"
    },
    {
      "name": "Fei Zhang"
    },
    {
      "name": "Shuo Han"
    },
    {
      "name": "Pengfei Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6ajgdpty3cav6.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.22849",
  "fulltext_url": null,
  "id": "6ajgdpty3cav6",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.22849",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1312|RNA and protein synthesis mechanisms"
    ]
  ],
  "openalex": "W7204164859",
  "pdf_url": "https://arxiv.org/pdf/2608.22849",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6ajgdpty3cav6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:29Z",
      "native_id": "2608.22849",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.22849"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling",
  "title_text": "RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:29Z",
  "url": "https://research.draconitic.com/paper/6ajgdpty3cav6",
  "venue": "arXiv",
  "versions": []
}