Logo

Mu Yuan (袁牧)

毋自欺,以诚意正心

AIoT Lab
The Chinese University of Hong Kong

Email ym0813@mail.ustc.edu.cn / muyuan@cuhk.edu.hk

Google Scholar
GitHub
ORCID

I am fortunate to work with Prof. Guoliang Xing at CUHK. Before joining CUHK, I was advised by Prof. Xiang-Yang Li and Prof. Lan Zhang at USTC. My research interest is building innovative networking systems for machine-learning model inference.

🎉 News

  • [May 2025] Our paper "RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service" has been accepted by ACL 2025!
  • [May 2025] Our paper "Argus: Multi-view egocentric human mesh reconstruction based on stripped-down wearable mmwave add-on" received the Best Paper Honorable Mention Award at SenSys 2025!
  • [Mar 2025] Our paper "SCX: Stateless KV-Cache Encoding for Cloud-Scale Confidential Transformer Serving" has been accepted by SIGCOMM 2025!
  • [Dec 2024] Received the CCF Doctoral Dissertation Award (10 Nationwide)!

Selected Publications

🔥 Large Language Models (LLMs)

SCX: Stateless KV-Cache Encoding for Cloud-Scale Confidential Transformer Serving
Mu Yuan, Lan Zhang, Liekang Zeng, Siyang Jiang, Bufang Yang, Di Duan, Guoliang Xing
Accepted by SIGCOMM 2025


RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
Yihang Cheng, Lan Zhang, Junyang Wang, Mu Yuan, Yunhao Yao
Accepted by ACL 2025


A-VL: Adaptive Attention for Large Vision-Language Models
Junyang Zhang, Mu Yuan, Ruiguang Zhong, Puhan Luo, Huiyou Zhan, Ningkang Zhang, Chengchen Hu, Xiangyang Li
AAAI 2025
PDF


Myotrainer: Muscle-Aware Motion Analysis and Feedback System for In-Home Resistance Training
Yuting He, Xinyan Wang, Mu Yuan, Di Duan, Doris SF Yu, Guoliang Xing, Hongkai Chen
SenSys 2024 (🏅 Best Demo Runner-Up Award)

💡 Mobile/Edge Intelligence

Argus: Multi-view egocentric human mesh reconstruction based on stripped-down wearable mmwave add-on
Di Duan, Shengzhe Lyu, Mu Yuan, Hongfei Xue, Tianxing Li, Weitao Xu, Kaishun Wu, Guoliang Xing
SenSys 2025 (🏅 Best Paper Honorable Mention Award)
PDF


PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale
Mu Yuan, Lan Zhang, Xuanke You, Xiang-Yang Li
ACM SIGCOMM 2023 (SIG Grant Award)
PDF | Slides | Code | Cite


InFi: End-to-end Learnable Input Filter for Resource-efficient Mobile-centric Inference
Mu Yuan, Lan Zhang, Fengxiang He, Xueting Tong, Xiang-Yang Li
ACM MobiCom 2022
PDF | Slides | Code | Bilibili | Cite

⚡️ Model Scheduling

MLink: Linking Black-Box Models from Multiple Domains for Collaborative Inference
Mu Yuan, Lan Zhang, Zimu Zheng, Yi-Nan Zhang, Xiang-Yang Li
IEEE TPAMI 2023
PDF | Cite


Efficient Deep Ensemble Inference via Query Difficulty-dependent Task Scheduling
Zichong Li, Lan Zhang, Mu Yuan, Miao-Hui Song, Qi Song
IEEE ICDE 2023


MLink: Linking Black-box Models for Collaborative Multi-model Inference
Mu Yuan, Lan Zhang, Xiang-Yang Li
AAAI 2022 (Oral 4.5%)
PDF | Slides (20min version) | Slides (1min version) | Code | Bilibili | Cite


Adaptive Model Scheduling for Resource-efficient Data Labeling
Mu Yuan, Lan Zhang, Xiang-Yang Li, Lin-Zhuo Yang, Hui Xiong
ACM TKDD 2022
PDF | Cite


Comprehensive and Efficient Data Labeling via Adaptive Model Scheduling
Mu Yuan, Lan Zhang, Xiang-Yang Li, Hui Xiong
IEEE ICDE 2020
PDF | Official Video | Bilibili | Slides | Cite

🎓 Doctoral Dissertation

异构协同模型推理 (Heterogeneous Collaborative Model Inference)
袁牧 (Mu Yuan)
🏆 CCF 全国优博 (CCF Doctoral Dissertation Award)
CCF 物联网专委优博 (CCF TCIoT Doctoral Dissertation Award)
中国科学技术大学校优博 (USTC Doctoral Dissertation Award)
PDF

🌐 Services

Reviewer of ACM IMWUT, IEEE INFOCOM, IEEE TMC, IEEE IoTJ, AAAI, NeurIPS
Co-chair of ANAI Workshop 2025 (co-located with ACM MobiCom 2025)


Funds and Awards

2024-2025 National Natural Science Foundation of China, Grant No.623B2093, RMB 300,000
2024 CCF Doctoral Dissertation Award (10 Nationwide) [Link]
2024 CCF TCIoT Doctoral Dissertation Award (4 Nationwide) [Link]
2024 USTC Doctoral Dissertation Award [Link]
2024 CAS President Award [Link]
2023 ByteDance Scholars Award (13 Nationwide) [Link]
2018 SenseTime Scholarship (22 Nationwide) [Link]
2018 Grand Price (1 out of 1530 teams) of the 4th National University Cloud Computing Contest [Link]