关注
In Gim
In Gim
Yale University
在 yale.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Memory-efficient DNN Training on Mobile Devices
I Gim, JG Ko
Proceedings of the 20th Annual International Conference on Mobile Systems …, 2022
442022
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
I Gim, G Chen, S Lee, N Sarda, A Khandelwal, L Zhong
Proceedings of Machine Learning and Systems, 325-338 6, 2024
282024
Fast Monte-Carlo Approximation of the Attention Mechanism
H Kim, JG Ko
Proceedings of the 36th AAAI Conference on Artificial Intelligence 36 (Vol …, 2022
12022
Confidential Prompting: Protecting User Prompts from Cloud LLM Providers
I Gim, C Li, L Zhong
arXiv preprint arXiv:2409.19134, 2024
2024
系统目前无法执行此操作，请稍后再试。
文章 1–4