Woosuk Kwon
Impact in
- Hardware and Architecture top 5%
- Parallel Computing and Optimization Techniques
- Artificial Intelligence top 5%
- Topic Modeling
- Natural Language Processing Techniques
- Security and Verification in Computing
Papers in
-
- Natural Language Processing Techniques 1
- Stochastic Gradient Optimization Techniques 1
-
- Caching and Content Delivery 1
- Advanced Data Storage Technologies 1
- Co-authors
- Joseph E. Gonzalez (1 shared paper)Ying Sheng (1 shared paper)Siyuan Zhuang (1 shared paper)Cody Hao Yu (1 shared paper)Ion Stoica (1 shared paper)L Zheng (1 shared paper)Tae Jun Ham (1 shared paper)Eojin Lee (1 shared paper)
- Journals
- IEEE Transactions on Broadcasting (1 paper)arXiv (Cornell University) (1 paper)Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (1 paper)
- Partner nations
- South KoreaUnited States
In The Last Decade
Woosuk Kwon
5 papers receiving 452 citations
Woosuk Kwon's Hit Papers
Peers
Comparison fields: 5 of 60
- Hardware and Architecture 86
- Artificial Intelligence 236
- Health Informatics 8
- Computer Vision and Pattern Recognition 91
- Computer Networks and Communications 101
Countries citing papers authored by Woosuk Kwon
This map shows the geographic impact of Woosuk Kwon's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Woosuk Kwon with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Woosuk Kwon more than expected).
Fields of papers citing papers by Woosuk Kwon
This network shows the impact of papers produced by Woosuk Kwon. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Woosuk Kwon. The network helps show where Woosuk Kwon may publish in the future.
Co-authors
The 19 scholars most cited alongside Woosuk Kwon, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | Efficient Memory Management for Large Language Model Serving with PagedAttention Hit paper breakdown → | 2023 | 329 |
| 2 | 2020 | 75 | |
| 3 | 2022 | 49 | |
| 4 | 2016 | 11 | |
| 5 | 2020 | 7 |
About Woosuk Kwon
Woosuk Kwon is a scholar working on Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition, Hardware and Architecture and Sociology and Political Science, having authored 5 papers that have together received 471 indexed citations. Recurring topics across this work include Parallel Computing and Optimization Techniques (2 papers), Advanced Neural Network Applications (2 papers), Video Coding and Compression Technologies (1 paper), Natural Language Processing Techniques (1 paper), Caching and Content Delivery (1 paper), Stochastic Gradient Optimization Techniques (1 paper), Advanced Data Storage Technologies (1 paper) and Multimedia Communication and Technology (1 paper). The work is most often cited by research in Hardware and Architecture (86 citations), Artificial Intelligence (236 citations), Health Informatics (8 citations), Computer Vision and Pattern Recognition (91 citations) and Computer Networks and Communications (101 citations). Woosuk Kwon has collaborated with scholars based in South Korea and United States. Frequent co-authors include Joseph E. Gonzalez, Ying Sheng, Siyuan Zhuang, Cody Hao Yu, Ion Stoica, L Zheng, Tae Jun Ham, Eojin Lee, Jung Ho Ahn and Jae W. Lee. Their work appears in journals such as IEEE Transactions on Broadcasting, arXiv (Cornell University) and Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.