Preprint · 2025 · Open access

CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration

Zhu, Pengyan, Tingting Yang

arXiv (Cornell University) · Published 20 May 2025 · DOI 10.48550/arxiv.2505.14085

Open PDFView at the publisherCite this paper

In brief

“CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration” is a 2025 preprint by Zhu, Pengyan and Tingting Yang, published in arXiv (Cornell University). OpenAlex counts 12 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
12
Most cited in
2026 (10)
References
29
Authors
2

Abstract

Emerging intelligent service scenarios in 6G communication impose stringent requirements for low latency, high reliability, and privacy preservation. Generative large language models (LLMs) are gradually becoming key enablers for the integration of semantic communication and computation. However, due to the limited computational resources of edge devices and the increasing complexity of heterogeneous terminal access, existing centralized inference approaches fail to meet the dual demands of response efficiency and data privacy in edge-side inference tasks. To address these challenges, this paper proposes a novel collaborative inference architecture that integrates cloud-based LLMs with edge-deployed small language models (SLMs), enabling dynamic scheduling and sharing of semantic-level intermediate states, and establishing a unified computation-communication paradigm tailored for 6G networks. Specifically, a key-value (KV) cache reuse mechanism is introduced to enhance the semantic understanding of edge models through contextual guidance from the cloud, while significantly reducing edge-side computational and storage overhead. Furthermore, a cross-node parallel scheduling mechanism is proposed to achieve asynchronous coordination between model state loading and decoding computation, thereby improving edge responsiveness. In addition, we investigate layer alignment and representation compression strategies between heterogeneous models to alleviate the communication burden on the edge. Experimental results demonstrate that the proposed architecture exhibits superior adaptability and scalability in terms of inference latency, system stability, and concurrent processing capacity.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Pengyan, Z., & Yang, T. (2025). CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.14085

MLA 9

Pengyan, Zhu,, and Tingting Yang. “CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2505.14085.

Chicago

Pengyan, Zhu, and Tingting Yang. 2025. “CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.14085.

Harvard

Pengyan, Z. and Yang, T. (2025) ‘CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration’, arXiv (Cornell University). doi:10.48550/arxiv.2505.14085.

IEEE

Z. Pengyan and T. Yang, “CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2505.14085.

BibTeX

@misc{pengyan2025lslm,
  title     = {{CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration}},
  author    = {Pengyan, Zhu, and Yang, Tingting},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2505.14085},
  url       = {https://doi.org/10.48550/arxiv.2505.14085}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing

  • large language model inference
  • cloud-edge collaboration
  • small language models
  • semantic communication
  • 6G
  • layer alignment
  • representation compression
  • data privacy

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Pengyan, Z., & Yang, T. (2025). CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.14085

How many times has this paper been cited?

12 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Zhu, Pengyan, Tingting Yang.

What is the DOI of this paper?

10.48550/arxiv.2505.14085, permanently at https://doi.org/10.48550/arxiv.2505.14085. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.