EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

VCU-LLM: Prompt-efficient On-device Large Language Model for Vague Command Understanding in Smart Homes

Zhengyuan Zhang, Dong Zhao, Tiancheng He, Zilong Wang, Xiangyu Li, Huadong Ma

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 15.06.2026 · 10 (2) · 1-30

DOI: 10.1145/3810190 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, online erschienen am 15.06.2026. Verfasst von Zhengyuan Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 111 Project, BUPT innovation and entrepreneurship support program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart homes are receiving growing interest in global markets. However, current smart home assistant systems either control appliances solely through users' explicit commands or rely on cloud-based large language models (LLMs) for vague command understanding, which brings drawbacks such as high latency, privacy concern, and high cost. In this work, we propose VCU-LLM, the first system to deploy LLMs on edge devices for local vague command understanding and smart device control plan generation. VCU-LLM introduces a novel vague command knowledge retrieval algorithm that refines device-related information in the input prompt, thereby accelerating the LLM's on-device inference and reducing task complexity. We further construct a dataset for LLM fine-tuning to simulate the use of smart home assistants in controlling devices across different households. During inference, a customized KV-cache technique is applied for further inference acceleration. Our evaluations with both human-based and LLM-based scoring demonstrate that VCU-LLM improves the quality of generated control plans by an average of 43.3% compared with SOTA baselines, while reducing time overhead by an average of 8.44x compared with other on-device baselines. We also implement VCU-LLM through a case study in a real home environment, demonstrating its feasibility in real-world application.

Förderung

  • National Natural Science Foundation of China
  • 111 Project
  • BUPT innovation and entrepreneurship support program

Zitieren

APA

Zhang, Z., Zhao, D., He, T., Wang, Z., Li, X., & Ma, H. (2026). VCU-LLM: Prompt-efficient On-device Large Language Model for Vague Command Understanding in Smart Homes. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 10(2), 1-30. https://doi.org/10.1145/3810190

Vancouver

Zhang Z, Zhao D, He T, Wang Z, Li X, Ma H. VCU-LLM: Prompt-efficient On-device Large Language Model for Vague Command Understanding in Smart Homes. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2026;10(2):1-30. doi:10.1145/3810190

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhengyuan and Zhao, Dong and He, Tiancheng and Wang, Zilong and Li, Xiangyu and Ma, Huadong},
  title = {VCU-LLM: Prompt-efficient On-device Large Language Model for Vague Command Understanding in Smart Homes},
  journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {1--30},
  doi = {10.1145/3810190}
}
Kostenlos starten →