In Gim

12 papers A* 2A 2Journal 7Unranked 1
YearRankTypeTitle / Venue / Authors
2025 A* conf
Cacheback: Speculative Decoding With Nothing But Cache.
EMNLP
Zhiyao Ma, In Gim, Lin Zhong
2025 J jnl
Cacheback: Speculative Decoding With Nothing But Cache.
CoRR
Zhiyao Ma, In Gim, Lin Zhong
2025 A* conf
Pie: A Programmable Serving System for Emerging LLM Applications.
SOSP
In Gim, Zhiyao Ma, SeungSeob Lee, Lin Zhong
2025 J jnl
Pie: A Programmable Serving System for Emerging LLM Applications.
CoRR
In Gim, Zhiyao Ma, SeungSeob Lee, Lin Zhong
2025 A conf
Serve Programs, Not Prompts.
HotOS
In Gim, Lin Zhong
2025 J jnl
Serve Programs, Not Prompts.
CoRR
In Gim, Lin Zhong
2025 J jnl
Wiretapping LLMs: Network Side-Channel Attacks on Interactive LLM Services.
IACR Cryptol. ePrint Arch.
Mahdi Soleimani, Grace Jia, In Gim, Seung-Seob Lee, Anurag Khandelwal
2024 J jnl
Asynchronous LLM Function Calling.
CoRR
In Gim, Seung-Seob Lee, Lin Zhong
2024 J jnl
Confidential Prompting: Protecting User Prompts from Cloud LLM Providers.
CoRR
In Gim, Caihua Li, Lin Zhong
2024 — conf
Prompt Cache: Modular Attention Reuse for Low-Latency Inference.
MLSys
In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, Lin Zhong
2023 J jnl
Prompt Cache: Modular Attention Reuse for Low-Latency Inference.
CoRR
In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, Lin Zhong
2022 A conf
Memory-efficient DNN training on mobile devices.
MobiSys
In Gim, JeongGil Ko
2023 — conf
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.
AISec
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
2026 — preprint
CCX: Enabling Unmodified Intel SGX Applications on Arm CCA.
arXiv
Matti Schulze, Thorsten Holz, Felix C. Freiling