访问量：
最后更新时间：--
访问量：
最后更新时间：--
欢迎对边缘智能（Edge Intelligence）、机器学习系统（ML Systems）及其相关安全问题感兴趣的本科生、硕士生、博士生加入我们的研究小组！
英雄不问出身，不论你来自哪所学校，哪个专业，我们看重的是思维方式、学习能力和做事态度。
✅ 我们欢迎这样的同学：
❌ 我们不太适合这样的同学：
如果你觉得自己适合，那我们很可能也在等你。欢迎邮件联系（pengli@xjtu.edu.cn），带上你的简历来我办公室喝喝咖啡，聊聊天。
------
关于我
李鹏，西安交通大学网络空间安全学院教授、博士生导师，国家级青年人才，西安交大青年拔尖A类。研究方向主要聚焦在边缘智能以及相关安全问题。这些年一直“蹲守边缘”，希望早日“云开见智”。
发表过一些论文，大概有150篇吧（没仔细数过，每年更新），不敢说全是精品，其中也有几篇还不错的A/B类论文（如IEEE INFOCOM，ACM SIGMOD，ACM HPDC，IEEE JSAC、IEEE TPDS、IEEE TC等）。感谢现在团队的小伙伴们！
拿过10余项最佳论文奖，其中还不错的有：IEEE Transactions on Computers年度最佳论文奖，IEEE通信协会大数据技术委员会最佳论文奖， IEEE计算机学会日本分会的年轻论文作者奖Young Author Award。
主持了一些科研项目，能养活团队，不让大家过苦日子。还有几项在申请中，拿到手了就在主页更新。
Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices [PDF]
EuroSys 2026
Fahao Chen, Jie Wan, Peng Li, Zhou Su, and Dongxiao Yu
Efficient Multimodal Serving via Module Multiplexing [PDF]
EuroSys 2026
Zicong Hong, Yuyan Chen, Haoyue Zhang, Peng Li, Wuhui Chen, Song Guo, and Xiaowei Shen
Communication-Efficient Sparsely-Activated Model Training via Sequence Migration and Token Condensation [PDF]
IEEE Transactions on Networking (CCF A)
Fahao Chen, Peng Li, Zicong Hong, Zhou Su, and Song Guo
Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency [PDF]
IJCAI 2025 (CCF A)
Ruixiao Li, Fahao Chen, and Peng Li
An Adaptive and Interpretable Congestion Control Service Based on Multi-Objective Reinforcement Learning
IEEE Transactions on Services Computing
Jiacheng Liu, Xu Li, Feilong Tang, Peng Li, Long Chen, J. Yu, Y. Zhu, P. Heng, and L. T. Yang
SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models [PDF]
IEEE INFOCOM 2025
Fahao Chen, Peng Li, Tom H. Luan, Zhou Su, and Jing Deng
Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management
IEEE INFOCOM 2025
Qianli Liu, Zicong Hong, Peng Li, Fahao Chen, and Song Guo
Tomtit: Hierarchical Federated Fine-Tuning of Giant Models based on Autonomous Synchronization
IEEE INFOCOM 2024
T. Qi, Y. Zhan, P. Li and Y. Xia
Value of Information: A Comprehensive Metric for Client Selection in Federated Edge Learning
IEEE Transactions on Computers
Y. Zou, S. Shen, M. Xiao, P. Li, D. Yu and X. Cheng
DGC: Training Dynamic Graphs with Spatio-temporal Non-uniformity using Graph Partitioning by Chunks
ACM SIGMOD 2024
F Chen, P Li, C Wu
Efficient Inference of Graph Neural Networks using Local Sensitive Hash
IEEE Transactions on Sustainable Computing
T. Liu, P. Li, Z. Su, and M. Dong
Adaptive Offloading of Transformer Inference for Weak Edge Devices with Masked Autoencoders
ACM Transactions on Sensor Networks
T Liu, P Li, Y Gu, P Liu, H Wang
Hwamei: A Learning-Based Synchronization Scheme for Hierarchical Federated Learning
IEEE ICDCS 2023
T Qi, Y Zhan, P Li, J Guo, Y Xia
A full list can be found at: DBLP
