About

I am a Ph.D. student in Computer Science at UC Berkeley Sky Computing Lab, advised by Ion Stoica. My research spans large language models (LLMs), data systems, and cloud computing, focusing on building post-training systems and pipelines for agentic and data-analytics workloads.

Previously, I received my B.S. in Computer Science (with honors) and Applied Math from the University of Wisconsin – Madison, where I was fortunate to be advised by Aditya Akella and Shivaram Venkataraman.

I’m always happy to connect with students interested in research or collaboration. If you’re interested, please send me an email at lshu [at] berkeley [dot] edu.

Recent Projects

SkyRL: A Modular Full-stack RL Library for LLMs

SkyRL is a modular, performant reinforcement learning library for LLMs, designed for real‑world agentic workloads.

[SkyRL GitHub] [SkyThought GitHub] [Blog Series]

Publications

Conference (Sort by Date)

• LLMs Can Easily Learn to Reason from Demonstrations – Structure, not content, is what matters!
  Dacheng Li*, Shiyi Cao*, Tyler Griggs*, Shu Liu*, Xiangxi Mo, Eric Tang, Sumanth Hegde, Kourosh Hakhamaneshi, Shishir G Patil, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
  EMNLP 2025.
  [paper] [code]

• Optimizing LLM Queries in Relational Data Analytics Workloads
  Shu Liu*, Asim Biswal*, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Joseph E. Gonzalez, Ion Stoica, Matei Zaharia
  MLSys 2025.
  [paper] [code]

• SkyStore: Cost-Optimized Object Storage Across Regions and Clouds
  Shu Liu, Xiangxi Mo, Moshik Hershcovitch, Henric Zhang, Audrey Cheng, Guy Girmonsky, Gil Vernik, Michael Factor, Soujanya Ponnapalli, Tiemo Bang, Natacha Crooks, Joseph E. Gonzalez, Danny Harnik, Ion Stoica
  VLDB 2025
  [paper] [code]

• Throughput-Oriented MoE Inference on Memory-Constraint GPUs
  Shiyi Cao, Shu Liu, Tyler Griggs, Peter Schafhalter, Xiaoxuan Liu, Ying Sheng, Joseph E. Gonzalez, Matei Zaharia, Ion Stoica
  ASPLOS 2025.
  [paper] [code]

• JENGA: Effective Memory Management for Serving LLM with Heterogeneity
  Chen Zhang, Kuntai Du, Shu Liu, Woosuk Kwon, Xiangxi Mo, Roger Wang, Xiaoxuan Liu, Kaichao You, Zhuohan Li, Jidong Zhai, Joseph E. Gonzalez, Ion Stoica
  SOSP 2025.
  [paper] [code]

• Cloudcast: High-Throughput, Cost-Aware Overlay Multicast in the Cloud
  Sarah Wooders, Shu Liu, Paras Jain, Xiangxi Mo, Joseph Gonzalez, Vincent Liu, Ion Stoica
  NSDI 2024
  [paper] [code]

• Darwin: Flexible Learning-Based CDN Caching
  Jiayi Chen, Nihal Sharma, Tarannum Khan, Shu Liu, Brain Chang, Aditya Akella, Sanjay Shakkottai, Ramesh K. Sitaraman
  SIGCOMM 2023
  [paper] [code]

Vision & Workshop Papers

• Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
  Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia, Alvin Cheung, Natacha Crooks, Joseph E. Gonzalez, Aditya G. Parameswaran
  CIDR 2026
  [paper]

• SkyRL-SQL: Matching GPT-4o and o4-mini on Text2SQL with Multi-Turn RL
  Shu Liu, Sumanth Hegde, Shiyi Cao, Alan Zhu, Dacheng Li, Tyler Griggs, Eric Tang, Akshay Malik, Kourosh Hakhamaneshi, Richard Liaw, Philipp Moritz, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
  NeurIPS 2025, Workshop on Multi-Turn Interactions in LLMs
  [blog]

• Text2SQL is Not Enough: Unifying AI and Databases with TAG
  Asim Biswal, Liana Patel, Siddharth Jha, Amog Kamsetty, Shu Liu, Joseph E. Gonzalez, Carlos Guestrin, Matei Zaharia
  CIDR 2025
  [paper] [code]

Preprints

• Barbarians at the Gate: How AI is Upending Systems Research
  Audrey Cheng*, Shu Liu*, Melissa Pan*, Zhifei Li, Bowen Wang, Alexander Krentsel, Tian Xia, Mert Cemri, Jongseok Park, Shuo Yang, Jeff Chen, Lakshya Agrawal, Aditya Desai, Jiarong Xing, Koushik Sen, Matei Zaharia, Ion Stoica
  [Arxiv][code]

• LEANN: A Low-Storage Vector Index
  Yichuan Wang, Zhifei Li, Shu Liu, Yongji Wu, Ziming Mao, Yilong Zhao, Xiao Yan, Zhiying Xu, Yang Zhou, Ion Stoica, Sewon Min, Matei Zaharia, Joseph E. Gonzalez
  [Arxiv] [code]

• Pie: Pooling CPU Memory for LLM Inference
  Yi Xu, Ziming Mao, Xiangxi Mo, Shu Liu, Ion Stoica
  [Arxiv]

Check out more recent preprints here!

Miscellaneous

• I’m a big soccer fan: a lifelong FC Bayern supporter and a part-time Man United follower. I’ve been to many Bundesliga matches in person and collected several player autographs over the years. Mia San Mia!

• I’m very into sports: running (5–10Ks and the occasional half marathon in Madison, Berkeley, and Saarbrücken), badminton, and both bouldering and rope climbing (indoors and recently outdoors).

• I enjoy a mix of music, literature, and travel:

  • 🎹 I love playing the piano and listening to classical.
  • 📚 I love reading. Find a list of books I’ve read here.
  • 🌍 I enjoy traveling and photography. Check out some of the photos I took here!