Zhiying Xu

Bio

Hi, my name is Zhiying Xu (徐至盈).

I am a Member of Technical Staff at AWS and work on systems for large ML models.

Before that, I earned my Ph.D. degree in the Dept. of Computer Science at Harvard University, working on systems and networking. I obtained my Bachelor's degree at Shanghai Jiao Tong University.

Email: xuzhiying9510 AT gmail.com, xzhiying AT amazon.com

Education

• Harvard Univerisity, Sept 2018 - June 2024
  PhD, Computer Science

• Shanghai Jiao Tong University, Sept 2014 - June 2018
  BE, Electronic Engineering

Experiences

• Amazon Web Services
  Member of Technical Staff, Apr 2026 -
  Applied Scientist, July 2024 - Apr 2026

• Google, July 2023 - Sept 2023
  Software Engineering Intern, Host: Tae Jun Ham

• Microsoft Research, June 2022 - Sept 2022
  Research Intern, Host: Francis Yan

Publication

• UCCL-Zip: Lossless Compression Supercharged GPU Communication
  Shuang Ma, ChonLam Lao, Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Zhen Jia, Jun Wu, Ion Stoica, Yida Wang, Yang Zhou
  Arxiv 2026

• UCCL-EP: Portable Expert-Parallel Communication
  Ziming Mao, Yihan Zhang, Chihan Cui, Zhen Huang, Kaichao You, Zhongjie Chen, Zhiying Xu, Zhenyu Gu, Scott Shenkert, Costin Raiciu, Yang Zhou, Ion Stoica
  OSDI 2026

• UCCL-Tran: An Extensible Software Transport Layer for GPU Networking
  Yang Zhou, Zhongjie Chen, Ziming Mao, ChonLam Lao, Shuo Yang, Pravein Govindan Kannan, Jiaqi Gao, Yilong Zhao, Yongji Wu, Kaichao You, Fengyuan Ren, Zhiying Xu, Costin Raiciu, Ion Stoica
  OSDI 2026

• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
  Haocheng Xi, Shuo Yang, Yilong Zhao, Muyang Li, Han Cai, Xingyang Li, Yujun Lin, Zhuoyang Zhang, Jintao Zhang, Xiuyu Li, Zhiying Xu, Jun Wu, Chenfeng Xu, Ion Stoica, Song Han, Kurt Keutzer
  ICML 2026

• StreamFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs
  Jiacheng Yang, Jun Wu, Yaoyao Ding, Zhiying Xu, Yida Wang, Gennady Pekhimenko
  CAIS 2026

• 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
  MLSys 2026 (Best Research Paper Award)

• Decouple and Decompose: Scaling Resource Allocation with DeDe
  Zhiying Xu, Minlan Yu, Francis Yan
  OSDI 2025

• ScaleFusion: Scalable Inference of Spatial-Temporal Diffusion Transformers for High-Resolution Long Video Generation
  Jiacheng Yang, Jun Wu, Zhen Zhang, Mason Fu, Zhiying Xu, Zhen Jia, Yida Wang, Gennady Pekhimenko
  MLSys 2025

• NetFlowGen: Leveraging Generative Pre-training for Network Traffic Dynamics
  Jiawei Zhou, Woojeong Kim, Zhiying Xu, Alexander M Rush, Minlan Yu
  Arxiv 2024

• Teal: Learning-Accelerated Optimization of WAN Traffic Engineering
  Zhiying Xu, Francis Yan, Rachee Singh, Justin Chiu, Alexander Rush, Minlan Yu
  SIGCOMM 2023

• Xatu: Boosting Existing DDoS Detection Systems Using Auxiliary Signals
  Zhiying Xu, Sivaramakrishnan Ramanathan, Alexander Rush, Jelena Mirkovic, Minlan Yu
  CoNEXT 2022

• Seeking the Truth in a Decentralized Manner
  Luoyi Fu, Jiasheng Xu, Shan Qu, Zhiying Xu, Xinbing Wang, Guihai Chen
  Transactions on Networking 2021

• Automating Botnet Detection with Graph Neural Networks
  Jiawei Zhou*, Zhiying Xu*, Alexander Rush, Minlan Yu
  *: co-primary authors
  AutoML Workshop of MLSys 2020

• Joint Optimization of Multicast Energy in Delay-Constrained Mobile Wireless Networks
  Luoyi Fu, Xinzhe Fu, Zesen Zhang, Zhiying Xu, Xudong Wu, Xinbing Wang, Songwu Lu
  Transactions on Networking 2018

• Complexity vs. Optimality: Unraveling Source-destination Connection in Uncertain Graphs
  Xinzhe Fu, Zhiying Xu, Qianyang Peng, Luoyi Fu, Xinbing Wang
  INFOCOM 2017

• ConMap: A Novel Framework for Optimizing Multicast Energy in Delay-constrained Mobile Wireless Networks
  Xinzhe Fu, Zhiying Xu, Qianyang Peng, Jie You, Luoyi Fu, Xinbing Wang, Songwu Lu
  MobiHoc 2017

• Determining Source–Destination Connectivity in Uncertain Networks: Modeling and Solutions
  Luoyi Fu, Xinzhe Fu, Zhiying Xu, Qianyang Peng, Xinbing Wang, Songwu Lu
  Transactions on Networking 2017

• De-Anonymization of Networks with Communities: When Quantifications Meet Algorithms
  Xinzhe Fu, Zhongzhao Hu, Zhiying Xu, Luoyi Fu, Xinbing Wang
  GLOBECOM 2017