Shixuan Sun 孙 世 轩

Shixuan Sun 孙 世 轩

Tenure-Track Associate Professor, Shanghai Jiao Tong University

Biography

Shixuan Sun is currently a Tenure-Track Associate Professor at the Department of Computer Science and Engineering, Shanghai Jiao Tong University. He is also a member of the EPCC Lab. His research interests are in parallel and distributed computing, machine learning and data-intensive applications.

He received his Ph.D. in Computer Sciences from the Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HKUST) in 2020, supervised by Prof. Qiong Luo. Prior to that, he got his M.S and B.S. in Computer Sciences from the School of Software Engineering, Tongji University in 2014 and 2011 respectively. From 2020 to 2023, he worked as a research fellow at the School of Computing, National University of Singapore, supervised by Prof. Bingsheng He. Additionally, he worked as a Software Development Engineer at Microsoft (Shanghai) from 2014 to 2015.

Contact

Email: [sunshixuan] AT [sjtu] DOT [edu] DOT [cn]

News

  • I am very honored to be selected as ACM SIGMOD China Rising Star Award!

  • 2026.9: FastTGM: Efficient Seed-Rooted Temporal Motif Counting with Compressed States was accepted to SIGMOD 2027. In this paper, we develop an efficient pattern-matching system for fraud detection. Congratulations to Mr. Sen Gao and Mr. Weitian Chen! Thanks to our collaborator from ByteDance.

  • 2026.9: InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models was accepted to ATC 2026.It is a scalable and efficient disaggregated LoRA serving system designed for multi-tenant environments. Congratulations to Mr. Hongyu Chen and Mr. Letian Ruan! Thanks to our collaborator from ByteDance.

  • 2026.9: Impeller: Scalable and Efficient Zero-Knowledge Proof Computation Framework via Graph Compilation was accepted to ASPLOS 2027. In this paper, we build an efficient compiler to accelerate ZK proof generation. Congratulations to Mr. Liukun Yu and Mr. Xinwei Qiang!

  • 2026.7: FluxZK: Scalable and Efficient Zero-Knowledge Proof Computation via GPU Acceleration was accepted to SC 2026. This is our first work on efficient privacy-preserving computing. Congratulations to Mr. Xinwei Qiang, Mr. Liukun Yu and Ms. Qianyu Wang!

  • 2026.6: Congratulations to Mr. Xinwei Qiang on receiving the Outstanding Bachelor’s Thesis Award of Shanghai Jiao Tong University, selected from more than 4,000 undergraduate students! Congratulations to Mr. Yikang Ruan on receiving the Outstanding Bachelor’s Thesis Award of the School of Computer Science, awarded to the top 3% of undergraduate students!

  • 2026.6: GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving was released on arXiv. An asynchronous execution runtime for DiT serving with support for dynamic parallelism, developed by Mr. Xinwei Qiang and Mr. Yifan Hu.

Open Positions

I’m looking for self-motivated PhD students, master’s students, and research assistants to join my group. If you’re interested in building high-performance, large-scale machine learning, data processing and privacy-preserving systems through algorithm-system co-design on modern hardware, please email me your CV.

Professional Services

Teaching Experiences

  • Lecturer, Shanghai Jiao Tong University CS1501 Programming Concepts and Methods (C++)
  • Lecturer, Shanghai Jiao Tong University CS2310 Operating System
  • Guest Lecturer, HKUST(GZ) DSAA6000D Graph Processing and Analytics, Accelerating Subgraph Query Processing on a Single Machine (2.5 hours tutorial in Sep 2022) [Slides]
  • Teaching Assistant, HKUST COMP5311 Database Architecture and Implementation
  • Teaching Assistant, HKUST MSBD5009 Parallel Programming

Honors & Awards

  • ACM SIGMOD China Rising Star Award 2026
  • LDBC SNB Interactive Benchmark World Champion Award 2026
  • Outstanding PC Award at ICDE 2025
  • The Championship of Alibaba POLARDB High Performance Competition (1/1808) [News][Code][Slides]
  • Hong Kong PhD Fellowship Award 2015-2019