Publications (7)
FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients
Leming Shen, Qiang Yang, Kaiyan Cui +4
Federated Learning (FL) facilitates collaborative training of a shared global model without exposing clients' private data. In practical FL systems, clients (e.g., edge servers, sm…
RANPilot: Making AI Functionalities Robust to Dynamic O-RAN Reconfigurations
Shiming Yu, Leming Shen, Jianing Zhang +4
RANPilot is a framework that uses a lightweight virtual O‑RAN emulator to generate training data for AI models before network reconfigurations, enabling proactive adaptation and cu…
Jailbreaking Embodied LLMs via Action-level Manipulation
Xinyu Huang, Qiang Yang, Leming Shen +2
Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level ris…
AutORAN: LLM-driven Natural Language Programming for Agile xApp Development
Xin Li, Shiming Yu, Leming Shen +3
Traditional RAN systems are closed and monolithic, stifling innovation. The openness and programmability enabled by Open Radio Access Network (O-RAN) are envisioned to revolutioniz…
Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models
Xinyu Huang, Leming Shen, Zijing Ma +1
Large Language Models (LLMs) have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smar…
AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
Leming Shen, Qiang Yang, Yuanqing Zheng +1
The advent of Large Language Models (LLMs) has profoundly transformed our lives, revolutionizing interactions with AI and lowering the barrier to AI usage. While LLMs are primarily…
GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development
Leming Shen, Qiang Yang, Xinyu Huang +2
Code Large Language Models (LLMs) enhance software development efficiency by automatically generating code and documentation in response to user requirements. However, code LLMs ca…