Yifan Yu

3107 Siebel Center
Urbana, IL, 61801
Greetings! I’m a Ph.D. student at Siebel School of Computing and Data Science in University of Illinois Urbana-Champaign, advised by Prof. Fan Lai.
I received my Bachelor’s degree in Computer Science from Georgia Institute of Technology, where I am very fortunate to work with Prof. Tuo Zhao. I am also very fortunate to spend a wonderful summer with Dr. Yu Gan and Prof. Fan Lai as a student researcher in Systems Research@Google in summer 2024, and with Dr. Moyan Li and Dr. Shaoyuan Xu as an applied scientist intern in Amazon in summer 2025.
My research interests lie in building efficient systems for supporting large language models, multi-agent systems, and GenAI. Our work has been trialed in real-world deployments.
news
Jul 18, 2025 | Paper IC-Cache: Efficient Large Language Model Serving via In-context Caching got accepted to SOSP’25 |
---|---|
May 19, 2025 | Joined Amazon as applied scientist intern |
Aug 23, 2024 | Joined UIUC and started Ph.D. journey advised by Prof. Fan Lai |
May 15, 2024 | Joined Systems Research@Google as a student researcher |
May 03, 2024 | Graduated from Georgia Institute of Technology |
selected publications
- IC-Cache: Efficient Large Language Model Serving via In-context CachingProceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles, 2025
- Loftq: Lora-fine-tuning-aware quantization for large language modelsThe Twelfth International Conference on Learning Representations, 2024
- Losparse: Structured compression of large language models based on low-rank and sparse approximationIn International Conference on Machine Learning, 2023