CSCheng Su

Cheng Su

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Cheng Su has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • HybridRAG-Based LLM Agents for Low-Carbon Optimization in Low-Altitude Economy Networks

    by Jinbo Wen, Cheng Su, Jiawen Kang, Jiangtian Nie, Yang Zhang, Jianhang Tang, Dusit Niyato, Chau Yuen

    Low-Altitude Economy Networks (LAENets) are emerging as a promising paradigm to support various low-altitude services through integrated air-ground infrastructure. To satisfy low-latency and high-computation demands, the integration of Unmanned Aerial Vehicles (UAVs) with Mobile Edge Computing (MEC) systems plays a vital role, which offloads computing tasks from terminal devices to nearby UAVs, enabling flexible and resilient service provisions for ground users. To promote the development of LAENets, it is significant to achieve low-carbon multi-UAV-assisted MEC networks. However, several challenges hinder this implementation, including the complexity of multi-dimensional UAV modeling and the difficulty of multi-objective coupled optimization. To this end, this paper proposes a novel Retrieval Augmented Generation (RAG)-based Large Language Model (LLM) agent framework for model formulation. Specifically, we develop HybridRAG by combining KeywordRAG, VectorRAG, and GraphRAG, empowering LLM agents to efficiently retrieve structural information from expert databases and generate more accurate optimization problems compared with traditional RAG-based LLM agents. After customizing carbon emission optimization problems for multi-UAV-assisted MEC networks, we propose a Double Regularization Diffusion-enhanced Soft Actor-Critic (R2DSAC) algorithm to solve the formulated multi-objective optimization problem. The R2DSAC algorithm incorporates diffusion entropy regularization and action entropy regularization to improve the performance of the diffusion policy. Furthermore, we dynamically mask unimportant neurons in the actor network to reduce the carbon emissions associated with model training. Simulation results demonstrate the reliability of the proposed HybridRAG-based LLM agent framework, which achieves a 6.6% improvement in F1 scores over traditional RAG, and validate the effectiveness of the R2DSAC algorithm, which outperforms the SAC algorithm by up to 64.17%.


  • Hybrid RAG-Empowered Multimodal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-Based Contract Approach

    by Cheng Su, Jinbo Wen, Jiawen Kang, Yonghua Wang, Yuanjia Su, Hudan Pan, Zishao Zhong, M. Shamim Hossain

    Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing demand for the Internet of Medical Things (IoMT) integration. The advent of generative artificial intelligence (GenAI) has further elevated multimodal large language models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can handle multimodal inputs and generate different kinds of data by utilizing large-scale training on massive multimodal datasets. Nevertheless, significant challenges remain in developing medical MLLMs, especially security and data freshness concerns, which impact the quality of MLLM outputs. To this end, this article proposes a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. The proposed framework enables secure data training by utilizing a hierarchical cross-chain design. Furthermore, it improves the output quality of MLLMs by using hybrid RAG that filters different unimodal RAG results using multimodal metrics and integrates these retrieval results as additional inputs for MLLMs. Furthermore, we utilize the age of information (AoI) to indirectly assess the influence of data freshness on MLLMs and apply contract theory to motivate healthcare data stakeholders to disseminate their current data, thereby alleviating information asymmetry in the data-sharing process. Finally, we employ a generative diffusion model-based deep reinforcement learning (DRL) technique to find the optimal contract for efficient data sharing. Numerical results show the effectiveness of the proposed approach in achieving secure and efficient healthcare data management.