In Gim
Ph.D. Student
Dept. of Computer Science
Yale University
Contact
51 Prospect St, New Haven, CT 06511
Office: Room 207, Arthur K. Watson Hall
Email: in.gim@yale.edu
I am a third-year Ph.D. student in the Department of Computer Science at Yale University,
where I work with Prof. Lin Zhong in the Efficient Computing Lab.
My research focuses on improving the efficiency of compound AI systems.
Before starting my Ph.D. program at Yale, I received my B.S. degree from Yonsei University in Korea in 2021.
Curriculum vitae. My name is 김인 in Hangul.
Recent news
- 2025. 04. Serve Programs, Not Prompts is accepted to HotOS.
- 2024. 12. Our work on asynchronous LLM function calling is now on arXiv.
- 2024. 09. Our work on confidential LLM prompting is available on arXiv.
- 2024. 02. Prompt Cache is accepted to MLSys 2024!
- 2023. 10. Our recent work on LLM prompt caching is on arXiv.
- 2022. 08. Starting my academic journey at Yale.
Publications
-
Serve Programs, Not Prompts
In Gim, and Lin Zhong
HotOS 2025, May 2025 (pdf) -
Wiretapping LLMs: Network Side-Channel Attacks on Interactive LLM Services
Mahdi Soleimani, Grace Jia, In Gim, Seung-Seob Lee, Anurag Khandelwal
Preprint, February 2025 (pdf) -
Asynchronous LLM Function Calling
In Gim, Seung-Seob Lee, and Lin Zhong
Preprint, December 2024 (pdf) -
Confidential Prompting: Protecting User Prompts from Cloud LLM Providers
In Gim†, Caihua Li†, and Lin Zhong
Preprint, September 2024 (code, pdf)
†Equal contributors -
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, and Lin Zhong
MLSys 2024, May 2024 (code, pdf) -
Memory-Efficient DNN Training on Mobile Devices
In Gim and JeongGil Ko
MobiSys 2022, July 2022 (code, pdf) -
Fast Monte-Carlo Approximation of the Attention Mechanism
Hyunjun Kim (In Gim) and JeongGil Ko
AAAI 2022, January 2022 (code, pdf)
Teaching
- Fall 2024 Principles of Computer System Design (CPSC 429)
Teaching Fellow - Spring 2024 Introduction to Systems Programming and Computer Organization (CPSC 323)
Teaching Fellow
Talks
- 2024. 09. LLM prompt caching
Invited talk at NVIDIA