Preprint · 2025 · Open access
CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration
arXiv (Cornell University) · Published 20 May 2025 · DOI 10.48550/arxiv.2505.14085
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
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
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.