{
  "abstract": "Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements. Phase-off interventions reveal non-uniform, model-specific rotary-phase dependence, while coverage interventions relate it to coverage-upgrade benefits. We propose profiling-guided layer-wise RoPE allocation, assigning high/low coverage under a fixed budget using early coverage-benefit profiles. The framework supports fixed-width query/key representations and physical rotary-dimension allocation in Multi-head Latent Attention (MLA). Normalized-depth mapping transfers profiles within model families, enabling small-model measurements to guide larger-model allocations before pretraining. A brief analysis relates selection and transfer to score calibration and inter-layer interactions. From-scratch experiments demonstrate validation-loss improvements over available budget-matched baselines, while analytical resource accounting identifies favorable quality--storage--compute trade-offs for physical MLA. These results connect positional demand to transferable, efficient architecture design.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.39223",
  "author_total": 3,
  "authors": [
    {
      "name": "Zhiwei Liu"
    },
    {
      "name": "Boao Kong"
    },
    {
      "name": "Bing Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/32k4aqs5r7896.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.39223",
  "fulltext_url": null,
  "id": "32k4aqs5r7896",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.39223",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.39223",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/32k4aqs5r7896.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:36:41Z",
      "native_id": "2610.39223",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.39223"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers",
  "title_text": "Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers",
  "type": "preprint",
  "updated_at": "2026-11-01T12:21:00Z",
  "url": "https://research.draconitic.com/paper/32k4aqs5r7896",
  "venue": "arXiv",
  "versions": []
}