Yuyuan Kang

University of Wisconsin-Madison

crop2.jpg

I am a Ph.D. student at the Department of Computer Sciences, University of Wisconsin-Madison. My research interests lie broadly in the area of Computer Systems and Data Management, including building efficient and scalable systems for data processing and analytics. I am currently working with Prof. Ming Liu.

Before that, I obtained my Master’s Degree in Software Engineering from Tsinghua University, where I was supervised by Prof. Jianmin Wang and worked closely with Prof Shaoxu Song and Xiangdong Huang. I did my undergraduate at Northeastern University (China).

My CV can be found here .

Publications

  1. NSDI’25
    Understanding and Profiling NVMe-over-TCP Using ntprof
    Yuyuan Kang and Ming Liu
    USENIX Symposium on Networked Systems Design and Implementation(NSDI), 2025
  2. SIGMOD’24
    Time Series Representation for Visualization in Apache IoTDB
    Lei Rui, Xiangdong Huang, Shaoxu Song, and 3 more authors
    ACM Special Interest Group on Management of Data(SIGMOD), 2024
  3. ICDE’22
    Separation or Not: On Handing Out-of-Order Time-Series Data in Leveled LSM-Tree
    Yuyuan Kang, Xiangdong Huang, Shaoxu Song, and 5 more authors
    International Conference on Data Engineering (ICDE), 2022
  4. DASFAA’20
    Heterogeneous Replicas for Multi-dimensional Data Management
    Jialin Qiao, Yuyuan Kang, Xiangdong Huang, and 4 more authors
    International Conference on Database Systems for Advanced Applications (DASFAA), 2020

Projects

EFabric

EFabric

EFabric is an elastic on-premise computing platform for AI4Science experiments. Researchers at UW-Madison can request, deploy, and run experiments on demands with high performance and low cost.

Benchmarking Vector Database

Benchmarking Vector Database

Benchmarking Vector Databases is a visualization platform that presents performance results from vectordbbench across different databases, indexes, and hardware settings. It provides an interactive way to explore QPS, latency, recall, and other metrics from large-scale vector search benchmarks.

ntprof

ntprof

ntprof is a systematic, informative, and lightweight NVMe-over-TCP profiler. The key idea is to view the NVMe/TCP storage substrate as a lossless switched network and apply network monitoring techniques. It models each on-path system module as a software switch, equips it with a programmable profiling agent on the data plane, and develops a proactive query interface for statistics collection and analysis.

Apache IoTDB

Apache IoTDB

Apache IoTDB is an industrial IoT time-series database management system that adopts a lightweight architecture with edge-cloud collaboration, supporting integrated collection, storage, management, and analysis of IoT time-series data.