{
  "abstract": "As LLMs grow in size, compression becomes increasingly important for efficient deployment. SVD-based low-rank compression reduces parameter counts but can degrade downstream performance. To improve performance after compression, we introduce QuLoC, a photonic quantum-assisted LLM compression algorithm that uses quantum circuit outputs to gate the retained low-rank components during training. Model performance is recovered through local functional reconstruction followed by end-to-end knowledge distillation. After training, the gating coefficients are absorbed into the low-rank factors, allowing the compressed model to run on classical hardware without executing quantum circuits during inference. Experiments on Qwen3.5-4B show that QuLoC achieves a 9.73\\% relative improvement in average accuracy over state-of-the-art baselines across multiple downstream tasks, demonstrating its effectiveness. We further evaluate QuLoC on LLaMA-7B at different parameter compression ratios. It achieves comparable or higher average downstream accuracy than state-of-the-art baselines, supporting its applicability to a larger model across different compression settings. These results motivate further exploration of photonic quantum-assisted compression for larger models and more complex agentic tasks.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.40146",
  "author_total": 7,
  "authors": [
    {
      "name": "Xiao-Hui Ni"
    },
    {
      "name": "Yu-Han Yao"
    },
    {
      "name": "Yu-Ze Zhu"
    },
    {
      "name": "Hang Song"
    },
    {
      "name": "Xiang Zhao"
    },
    {
      "name": "Lin Yang"
    },
    {
      "name": "Xian-Min Jin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7v9w68g9w9jcv.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.40146",
  "fulltext_url": null,
  "id": "7v9w68g9w9jcv",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.40146",
  "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",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7215053651",
  "pdf_url": "https://arxiv.org/pdf/2609.40146",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7v9w68g9w9jcv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2609.40146",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.40146"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "QuLoC: Photonic Quantum-Assisted Low-Rank LLM Compression",
  "title_text": "QuLoC: Photonic Quantum-Assisted Low-Rank LLM Compression",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:45Z",
  "url": "https://research.draconitic.com/paper/7v9w68g9w9jcv",
  "venue": "arXiv",
  "versions": []
}