5 papers
OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
Liujianfu Wang, Yuyang Du, Yuchen Pan +3
Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices wi…
KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
Xilin Dang, Kexin Chen, Xiaorui Su +7
In clinical practice, physicians refrain from making decisions when patient information is insufficient. This behavior, known as abstention, is a critical safety mechanism preventi…
IndusGCC: A Data Benchmark and Evaluation Framework for GUI-Based General Computer Control in Industrial Automation
Xiaoran Yang, Yuyang Du, Kexin Chen +14
As Industry 4.0 progresses, flexible manufacturing has become a cornerstone of modern industrial systems, with equipment automation playing a pivotal role. However, existing contro…
Cellular-X: An LLM-empowered Cellular Agent for Efficient Base Station Operations
Liujianfu Wang, Xinyi Long, Yuyang Du +3
This paper introduces Cellular-X, an LLM-powered agent designed to automate cellular base station (BS) maintenance. Leveraging multimodal LLM and retrieval-augmented generation (RA…
The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?
Yiyi Zhang, Xingyu Chen, Kexin Chen +3
Recent years have witnessed extensive efforts to enhance Large Language Models (LLMs) across various domains, alongside growing attention to their ethical implications. However, a…