About Me

Hi, I’m Lily (Xiaoxuan) Liu. I’m currently a researcher at OpenAI. Before joining OpenAI, I completed my PhD in Computer Science at UC Berkeley, where I was part of Sky Lab (formerly RISE/AMP Lab) and was fortunate to be advised by Professor Alvin Cheung and Professor Ion Stoica. I received my undergraduate degree from Peking University and my master’s degree from Carnegie Mellon University, where I had the pleasure of working with Andy and Huanchen.

Research Interest: Understand and build AGI :). During my PhD, I built system and was part of the vllm team.

Blogs I Wrote Occasionally

• Online Speculative Decoding
• vLLM Speculative Decoding

Selected Publication and Manuscripts

• Speculative Decoding: Performance or Illusion?, MLsys 2026.
  Xiaoxuan Liu^*, Jiaxiang Yu^*, Jongseok Park, Ion Stoica, Alvin Cheung
• Optimizing Speculative Decoding for Serving Large Language Models Using Goodput, arxiv, 2024.
  Xiaoxuan Liu, Cade Daniel, Langxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang
• Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity, arxiv, 2024. [code]
  Tyler Griggs^*, Xiaoxuan Liu^*, Jiaxiang Yu, Doyoung Kim, Wei-Lin Chiang, Alvin Cheung, Ion Stoica
• Online Speculative Decoding, ICML 2024. [code][blog]
  Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang
• Leveraging Application Data Constraints to Optimize Database-Backed Web Applications, VLDB 2023. [code]
  Xiaoxuan Liu, Shuxian Wang, Mengzhu Sun, Sicheng Pan, Ge Li, Siddharth Jha, Cong Yan, Junwen Yang, Shan Lu, Alvin Cheung.
• GACT: Activation Compressed Training for Generic Network Architectures, ICML 2022. [code][slides][talk]
  Xiaoxuan Liu, Lianmin Zheng, Dequan Wang, Yukuo Cen, Weize Chen, Xu Han, Jianfei Chen, Zhiyuan Liu, Jie Tang, Joey Gonzalez, Michael Mahoney, Alvin Cheung.
• Order-Preserving Key Compression for In-Memory Search Trees, SIGMOD 2020. [code][slides][talk]
  Huanchen Zhang, Xiaoxuan Liu, David Anderson, Michael Kaminsky, Kimberly Keeton, Andrew Pavlo.

Papers that die silently I do randomly

• An Evaluation of Memory Optimization Methods for Training Neural Networks, arxiv, 2023
  Xiaoxuan Liu, Siddharth Jha, Alvin Cheung