Qianliang Wu

Qianliang Wu

I am a Ph.D. student in Computer Sciences at the University of Wisconsin-Madison, advised by Ming Liu at NetLab.

My research lies at the intersection of networked systems and machine learning, with a focus on how ML systems interact with the physical world through sensors. Currently, I build efficient serving systems for time-series and VLA models. More broadly, I aim to build a unified systems stack for Physical AI.

Before Wisconsin, I received my B.Eng. in Software Engineering, with a minor in Statistics, from Tsinghua University. There I worked with Bo Wang on learning-based congestion control, and spent summer 2023 with Bhaskar Krishnamachari at USC.

I am looking for research internships for summer 2027. Feel free to reach out!

GitHub LinkedIn Blog qwu293 [at] wisc [dot] edu

Preprints

  • Obelisk: Exploiting Temporal Semantics for Time-Series Model Serving (under submission, 2026) Qianliang Wu, Ming Liu

Projects

  • HBServe: an open-source serving engine for time-series foundation models, built on the time predicate from Obelisk [code]
  • HBridge: bridging heterogeneous physiological sensors to cloud model inference [website]

Teaching

  • Teaching Assistant, CS640: Introduction to Computer Networks (UW-Madison, Spring 2025)

Education

  • Ph.D. in Computer Sciences, University of Wisconsin-Madison (2024–present)
  • B.Eng. in Software Engineering, Minor in Statistics, Tsinghua University (2020–2024)

Honors

  • Scholarship for Technology Innovation and Excellence (Tsinghua, 2023)
  • Tsinghua University Challenge Cup, 3rd Prize (2023)
  • Scholarship for Academic Excellence (Tsinghua, 2021)