HELLO! 👋

I am a Scientist at EPFL, working with Prof. Rachid Guerraoui in the Distributed Computing Lab. Previously, I was a Postdoctoral Fellow at HKUST, working with Prof. Song Guo in the HK PEILab.
‍
My research lies at democratizing access to AI by harnessing the combined potential of cloud, edge, and end-computing nodes. The goal is to deliver AI services that are cost-effective, trustworthy, and equitable, enabling diverse users and applications to access advanced AI technologies.

Academic Qualifications

The Hong Kong Polytechnic University

Doctor of Philosophy in Computer Science with HKPFS

Advisor: Prof. Song Guo

Hong Kong

09/2020 ‑ 01/2025

University of Aizu

Visting Scholar

Advisor: Prof. Peng Li

Japan

07/2024‑08/2024

ETH Zürich

Visiting Scholar

Advisor: Prof. Roger Wattenhofer

Switzerland

04/2023‑10/2023

Sun Yat‑sen University

Bachelor of Engineering in Software Engineering

Advisor: Prof. Wuhui Chen

China

09/2015‑07/2020

Recent Publication Highlights

Efficient Multimodal Serving via Module Multiplexing,
Zicong Hong, Yuyan Chen, Haoyue Zhang, Peng Li, Wuhui Chen, Song Guo, and Xiaowei Shen.
in European Conference on Computer Systems (EuroSys), 2026.
D2MoE: Dual Routing and Dynamic Scheduling forEfficient On-Device MoE-based LLM Serving,
Haodong Wang, Qihua Zhou, Zicong Hong* and Song Guo. (*corresponding author)
in IEEE International Conference on Computer Communications (MOBICOM), 2025.
Obscura: Concealing Recomputation Overhead in Training of Large Language Models with Bubble-filling Pipeline Transformation,
Yuzhou Huang, Yapeng Jiang, Zicong Hong, Wuhui Chen, Bin Wang, Weixi Zhu, Yue Yu, and Zibin Zheng.
in USENIX Annual Technical Conference , 2025.
Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline,
Zhiyuan Fang, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu, Fan Yu, and Zibin Zheng.
in ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.
Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management,
Qianli Liu, Zicong Hong*, Fahao Chen, Peng Li and Song Guo. (*corresponding author)
in IEEE International Conference on Computer Communications (INFOCOM), 2025.
Optimus: Warming Serverless ML Inference via Inter-Function Model Transformation,
Zicong Hong, Jian Lin, Song Guo, Sifu Luo, Wuhui Chen, Roger Wattenhofer and Yue Yu.
in European Conference on Computer Systems (EuroSys), 2024.
OTAS: An Elastic Transformer Serving System via Token Adaptation,
Jinyu Chen, Wenchao Xu, Zicong Hong*, Song Guo, Haozhao Wang, Jie Zhang and Deze Zeng. (*corresponding author)
in IEEE International Conference on Computer Communications (INFOCOM), 2024.
GriDB: Scaling Blockchain Database via Sharding and Off-Chain Cross-Shard Mechanism,
Zicong Hong, Song Guo, Enyuan Zhou, Wuhui Chen, Huawei Huang and Albert Zomaya.
in International Conference on Very Large Data Bases (VLDB), 2023.

Zicong Hong

Ph.D.

HELLO! 👋

Recent News

Professional Experience

École Polytechnique Fédérale de Lausanne