Yiming Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiming Li has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Tingjun Chen
Duke University, Durham, USA
6 shared publications - Yiran Chen
Duke University, Durham, North Carolina, USA
3 shared publications - Mingchen Ma
Duke University, Durham, USA
2 shared publications - Ningyuan Yang
Duke University, Durham, USA
2 shared publications - Ang Li
University of Maryland College Park
1 shared publication - Beidi Chen
Carnegie Mellon University
1 shared publication
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1684-1686
WiP: Constructing Wireless Digital Twins Using Heterogeneous Geospatial Data Sources
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1684-1686
Open AccessWiP: Constructing Wireless Digital Twins Using Heterogeneous Geospatial Data Sources
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 8-14
5G × Headsets: An Application-Level Measurement Study of 5G Latency for Networked Immersive XR
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 8-14
Open Access5G × Headsets: An Application-Level Measurement Study of 5G Latency for Networked Immersive XR
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1248-1252
Skilled AI Agents for Embedded and IoT Systems Development
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1248-1252
Open AccessSkilled AI Agents for Embedded and IoT Systems Development
- Top Cited PapersOpen Access
- 25 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 127-132
DecodeX: Exploring and Benchmarking of LDPC Decoding Across CPU, GPU, and ASIC Platforms
- 25 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 127-132
Top Cited PapersOpen AccessDecodeX: Exploring and Benchmarking of LDPC Decoding Across CPU, GPU, and ASIC Platforms
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-80
IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-80
Open AccessIoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1775-1777
Federated Black-box Prompt Tuning System for Large Language Models on the Edge
Federated learning (FL) offers a privacy-preserving way to train models across decentralized data. However, fine-tuning pre-trained language models (PLMs) in FL is challenging due to restricted model parameter access, high computational demands, and communication overheads. Our method treats large language models (LLMs) as black-box inference APIs, optimizing prompts with gradient-free methods. This approach, FedBPT, reduces exchanged variables, boosts communication efficiency, and minimizes computational and memory costs. We demonstrate the practical implementation of FedBPT on resource-limited edge devices, showcasing its ability to efficiently achieve collaborative on-device LLM fine-tuning.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1775-1777
Open AccessFederated Black-box Prompt Tuning System for Large Language Models on the Edge
Federated learning (FL) offers a privacy-preserving way to train models across decentralized data. However, fine-tuning pre-trained language models (PLMs) in FL is challenging due to restricted model parameter access, high computational demands, and communication overheads. Our method treats large language models (LLMs) as black-box inference APIs, optimizing prompts with gradient-free methods. This approach, FedBPT, reduces exchanged variables, boosts communication efficiency, and minimizes computational and memory costs. We demonstrate the practical implementation of FedBPT on resource-limited edge devices, showcasing its ability to efficiently achieve collaborative on-device LLM fine-tuning.