CV
My curriculum vitae. The PDF is generated from `_data/cv.yml` by RenderCV.
Contact Information
| Name | Jialiang Gu |
| Professional Title | Ph.D. Student in Computer Science |
| jgu7@gmu.edu | |
| Phone | +1 571-234-2933 |
| Website | https://gujialiang123.github.io |
Summary
- First-year Ph.D. student in Computer Science at George Mason University, advised by Prof. Keren Zhou. I also collaborate closely with Prof. Jialu Zhang at the University of Waterloo. My research interests focus on machine learning systems, LLM applications, and teaching and learning in the LLM era.
Education
-
2025 - present Fairfax, VA, USA
Ph.D. Student
George Mason University
Computer Science
- Advisor: Prof. Keren Zhou
-
2021 - 2025 Wuhan, China
Undergraduate
Wuhan University
Computer Science, Hongyi Honor College
- Overall GPA: 3.72/4.0
Published / Accepted Papers
-
2027 NKI Teaching Lab: An Accelerator-Free Toolchain for Learning Tile-Level AI Accelerator Programming
SIGCSE TS 2027 (accepted)
Jialiang Gu, Junjie Ma, Thai-Hoa Nguyen, Hao Wu, Zhicong Lu, Shuyin Jiao, Binqian Yin, and Keren Zhou. Accepted to SIGCSE TS 2027.
-
2026 Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
AACL-IJCNLP 2026 (accepted)
Zhikai Chen*, Jialiang Gu*, Junyu Yin*, Xianxuan Long, Shenglai Zeng, Xiaoze Liu, Kai Guo, Keren Zhou, and Jiliang Tang. Accepted to AACL-IJCNLP 2026. * Equal contribution (co-first authors).
-
2026 TileBench: A Controlled Benchmark for Performance Evaluation and Bottleneck Diagnosis of Tile-Based Programming Models
AACL-IJCNLP 2026 (accepted)
Bowen Cui, Zhongchun Zhou, Hao Wu, Tejas Ramesh, Junyu Yin, Jialiang Gu, and Keren Zhou. Accepted to AACL-IJCNLP 2026.
-
2026 FrontierCS: Evolving Challenges for Evolving Intelligence
ICML
Qiuyang Mang*, Wenhao Chai*, Zhifei Li*, Huanzhi Mao*, Shang Zhou*, Alexander Du*, Hanchen Li*, Shu Liu*, Edwin Chen, Yichuan Wang, Xieting Chu, Zerui Cheng, Yuan Xu, Tian Xia, Zirui Wang, Tianneng Shi, Jianzhu Yao, Yilong Zhao, Qizheng Zhang, Charlie F. Ruan, Zeyu Shen, Kaiyuan Liu, Zhaoyang Hong, Alex Gu, Ziyi Zhang, Runyuan He, Dong Xing, Zerui Li, Zirong Zeng, Yige Jiang, Lufeng Cheng, Ziyi Zhao, Youran Sun, Suyang Zhong, Junpeng Wang, Donglin Li, Wenyuan Huang, Jialiang Gu, Wesley Kai Zheng, Wangmeiyu Zhang, Ruyi Ji, Xuechang Tu, Zihan Zheng, Zhaozi Wang, Zexing Chen, Jingbang Chen, Jialu Zhang, Aleksandra Korolova, Peter Henderson, Pramod Viswanath, Vijay Ganesh, Saining Xie, Zhuang Liu, Dawn Song, Sewon Min, Ion Stoica, Joseph E. Gonzalez, Jingbo Shang, and Alvin Cheung. ICML, 2026. * Equal contribution (co-first authors).
-
2026 Context-Aware Feedback Compression in Online Judge Programming with LLMs
FSE-IVR
Jialiang Gu, Keren Zhou, Daming Li, Hanyuan Shi, and Jialu Zhang. FSE-IVR, 2026.
arXiv / Manuscripts
-
2025 A Systematic Study of Time Limit Exceeded Errors in Online Programming Assignments
arXiv:2510.14339 [cs.SE]
Jialiang Gu*, Jialu Zhang*, Wangmeiyu Zhang, José Pablo Cambronero, John Kolesar, Ruzica Piskac, Daming Li, and Hanyuan Shi. arXiv:2510.14339 [cs.SE], 2025. * Equal contribution (co-first authors).
-
2025 DiscoSum: Discourse-aware News Summarization
arXiv:2506.06930 [cs.SE]
Jia-Liang Gu*, Tenghao Huang*, Alexander Spangher*, Jiatong Shi, and Muhao Chen. arXiv:2506.06930 [cs.SE], 2025. * Equal contribution (co-first authors).
Work Experience
-
May 2026 - Aug 2026 Redmond, WA, USA
Research Intern, AIFX Group
Microsoft Research
Worked on regime-aware LLM inference optimization, improving LLM serving performance across diverse workload patterns on NVIDIA H200 GPUs.
- Built an automated profiling and tuning pipeline for SGLang, exploring server-level configurations across long-context and concurrent workloads, including scheduling, chunked prefill, CUDA graphs, memory allocation, and attention/MoE backends.
- Achieved up to 2.2× end-to-end speedup over the baseline in long-context regimes through workload-specific server optimization.
- Investigated kernel-level performance bottlenecks in prefill and decoding, using GPU profiling, correctness validation, and targeted kernel optimizations to reduce memory movement and improve execution efficiency.
- Designed extensive ablation and transferability studies to understand when optimizations generalize across workloads, including synthetic regimes and agentic workloads such as ToolAgent.
- Explored a workload-aware multi-server routing design that dispatches requests to specialized server configurations based on workload characteristics.
- Contributed performance findings, bug reports, and fixes upstream to the SGLang open-source project.
Research Experience
-
2023 - 2025 Waterloo, Canada
Research Assistant
University of Waterloo
Study on Time Limit Exceeded errors characteristics in competitive programming.
- Advisor: Prof. Jialu Zhang
-
Jul 2024 - Sep 2024 Davis, CA, USA
Research Intern
University of California, Davis
Structural summarization with large language models.
- Advisor: Prof. Muhao Chen
Academic Competition Awards
-
2024 Champion, 2024 ICPC China Hubei Provincial Contest (Wuhan)
ICPC China Hubei Provincial Contest
-
2023 Gold Medal, International Collegiate Programming Contest (ACM-ICPC) Hangzhou Regional Contest
ACM-ICPC
-
2024 Bronze Medal, International Collegiate Programming Contest (ACM-ICPC) EC-Final
ACM-ICPC East Asia Final
-
2023 Silver Medal, International Collegiate Programming Contest (ACM-ICPC) Macau Regional Contest
ACM-ICPC
-
2022 Silver Medal, International Collegiate Programming Contest (ACM-ICPC) Xi'an Regional Contest
ACM-ICPC
-
2022 Silver Medal, International Collegiate Programming Contest (ACM-ICPC) Nanjing Regional Contest
ACM-ICPC
-
2023 Gold Medal, 2023 ICPC China Shaanxi National Invitational Programming Contest (Xi'an)
ICPC China
-
2023 Gold Medal, 2023 CCPC China Hunan National Invitational Programming Contest (Xiangtan)
CCPC China
-
2023 Silver Medal, The 9th China Collegiate Programming Contest (Shenzhen)
CCPC
-
2022 Silver Medal, The 8th China Collegiate Programming Contest (Weihai)
CCPC
-
2023 First Prize, 2023 RAICOM Robotics Challenge national finals
RAICOM Robotics Challenge
-
2023 Third Prize, The 2nd CCF Siannan Cup Quantum Computing Challenge
CCF
Honors and Experience at School
-
2024 Excellent Teaching Assistant, Computer Composition and Design
School of Computer Science, Wuhan University
-
2024 Excellent Student, Hongyi Honor College, Wuhan University (Top 15%)
Wuhan University
-
2024 CCF Excellent Student, CCF National Outstanding College Student Award
China Computer Federation
-
2022 Assistant Head Teacher, Hongyi Honor College, Wuhan University
Wuhan University
Technical Skills
Projects
-
Triton-Viz
Core developer of an open-source project.
- Developed and maintained the visualizer module, focusing on extending Triton-Viz to support additional tile-level languages and improving its visualization infrastructure.
-
32-bit Pipelined CPU based on RISC-V
Verilog personal project, Wuhan.
- Implemented a 32-bit pipelined RISC-V CPU in Verilog, supporting 32 basic instructions and successfully running C/C++-compiled programs and an FPGA-deployed aircraft shooting game.
-
Tripo APP
Test engineer and project manager for a large-scale software application design course project.
- Built a travel diary app with post sharing, GPT-based summary generation, and AI-powered hotspot recommendation features.
Research Interests
- Machine learning systems (MLSys)
- LLM applications for code understanding, analysis, and explanation
- Ecosystem tools for next-generation GPU programming languages such as Triton
- LLM reasoning and reliability with static analysis and agent-based methods
Others
- Codeforces homepage: https://codeforces.com/profile/gujialiang123
- Language: English (CET-4 562)