Hi I’m Xuting Liu

I’m a Ph.D. student at UPenn’s Distributed Systems Lab advised by Vincent Liu.

Before joining UPenn, I got my bachelor’s degree in Computer Science and Operations Research at UC Berkeley, where I interned at the Sky Lab advised by Joseph Gonzalez and Paras Jain.

Check out my CV here!

Research Interests

Machine learning systems, collective communications, systems for dynamic LLM: Early Exit, Speculative Decoding, and Multi-Token Prediction.

Recent Publication

1. 𝝀-trim: Optimizing Function Initialization in Serverless Applications With Cost-driven Debloating. Xuting Liu*, Spyros Pavlatos*, Yuhao Liu, Vincent Liu (* Equal contribution). ASPLOS 25. (To be presented in ASPLOS 26)

   [Link] [Code]

   Artifact available Artifact functional

2. Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem. Xuting Liu, Behnaz Arzani, Siva Kesava Reddy Kakarla, Liangyu Zhao, Vincent Liu, Miguel Castro, Srikanth Kandula, Luke Marshall. SIGCOMM 24.

   [Link] [Code]

   Artifact available Artifact functional

Recent Work Experience

Google Systems Research Group, Seattle

11/2025 - 02/2026

Prefill-Decode disaggregated LLM inference optimization

AWS Deep Science, Santa Clara

08/2025 - 10/2025

Prefill-Decode disaggregated LLM inference simulation

Microsoft Research Asia, Beijing

07/2024 - 10/2024

Distributed ML Systems

Mentor: Jilong Xue

Microsoft Research, Redmond

12/2023 - 12/2024

GPU collective communication

Mentors: Behnaz Arzani and Siva Kesava Reddy Kakarla