M
Moonkyung Ryu
Researcher at Google
Publications - 15
Citations - 313
Moonkyung Ryu is an academic researcher from Google. The author has contributed to research in topics: Flash file system & Flash memory. The author has an hindex of 7, co-authored 11 publications receiving 217 citations. Previous affiliations of Moonkyung Ryu include Georgia Institute of Technology.
Papers
More filters
Proceedings Article
Data Center Cooling using Model-predictive Control
TL;DR: Adopting a data-driven, model-based approach, it is demonstrated that an RL agent with little prior knowledge is able to effectively and safely regulate conditions on a server floor after just a few hours of exploration, while improving operational efficiency relative to existing PID controllers.
Proceedings ArticleDOI
What is a good buffer cache replacement scheme for mobile flash storage
TL;DR: This paper proposes a new buffer cache replacement scheme called SpatialClock, and exposes the limitations of current buffer cache performance evaluation methods, and proposes a novel evaluation framework that is a hybrid between trace-driven simulation and real implementation of such schemes inside an operating system.
Journal ArticleDOI
Aligning Text-to-Image Models using Human Feedback
Kimin Lee,Hao Liu,Moonkyung Ryu,Olivia Watkins,Yuqing Du,C. Boutilier,Pieter Abbeel,Mohammad Ghavamzadeh,Shixiang Gu +8 more
TL;DR: This article proposed a fine-tuning method for aligning text-to-image models using human feedback, comprising of three stages: collecting human feedback assessing model output alignment from a set of diverse text prompts, then using the human-labeled image-text dataset to train a reward function that predicts human feedback.
Posted Content
CAQL: Continuous Action Q-Learning
TL;DR: This work develops CAQL, a (class of) algorithm(s) for continuous-action Q-learning that can use several plug-and-play optimizers for the max-Q problem, and compares it with state-of-the-art RL algorithms on benchmark continuous-control problems that have different degrees of action constraints.
Proceedings ArticleDOI
Impact of flash memory on video-on-demand storage: analysis of tradeoffs
TL;DR: This paper analyzes tradeoffs and potential impact that flash memory SSD can have for a VoD server, and claims that interval caching cannot be used with it, and proposes using file-level Least Frequently Used (LFU) due to the highly skewed video access pattern of the VoD workload.