Jiwon Seo

Jiwon Seo

Auto-generated profile, based on publicly available information

Jiwon Seo

Seoul National University, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 April 2024
Verified
Conference Paper
Open access
HOHyungjun Oh
Hyungjun Oh
KKKihong Kim
Kihong Kim
JKJaemin Kim
Jaemin Kim
SKSungkyun Kim
Sungkyun Kim
JLJunyeol Lee
Junyeol Lee
JSJiwon Seo
Jiwon Seo
This paper presents ExeGPT, a distributed system designed for constraint-aware LLM inference. ExeGPT finds and runs with an optimal execution schedule to maximize inference throughput while satisfying a given latency constraint. By leveraging the distribution of input and output sequences, it effectively allocates resources and determines optimal execution configurations, including batch sizes and partial tensor parallelism. We also introduce two scheduling strategies based on Round-Robin Allocation and Workload-Aware Allocation policies, suitable for different NLP workloads. We evaluate ExeGPT on six LLM instances of T5, OPT, and GPT-3 and five NLP tasks, each with four distinct latency constraints. Compared to FasterTransformer, ExeGPT achieves up to 15.2× improvements in throughput and 6× improvements in latency. Overall, ExeGPT achieves an average throughput gain of 2.9× across twenty evaluation scenarios. Moreover, when adapting to changing sequence distributions, the cost of adjusting the schedule in ExeGPT is reasonably modest. ExeGPT proves to be an effective solution for optimizing and executing LLM inference for diverse NLP workload and serving conditions.

16 July 2020 in ACM Transactions on Storage
Verified
Journal Article
Open access
HCHokeun Cha
Hokeun Cha
MNMoohyeon Nam
Moohyeon Nam
KJKibeom Jin
Kibeom Jin
JSJiwon Seo
Jiwon Seo
BNBeomseok Nam
Beomseok Nam
In this work, we propose B 3 -tree , a hybrid index for persistent memory that leverages the byte-addressability of the in-memory index and the page locality of B-trees. As in the byte-addressable in-memory index, B 3 -tree is updated by 8-byte store instructions. Also, as in disk-based index, B 3 -tree is failure-atomic since it makes every 8-byte store instruction transform a consistent index into another consistent index without the help of expensive logging. Since expensive logging becomes unnecessary, the number of cacheline flush instructions required for B 3 -tree is significantly reduced. Our performance study shows that B 3 -tree outperforms other state-of-the-art persistent indexes in terms of insert and delete performance. While B 3 -tree shows slightly worse performance for point query performance, the range query performance of B 3 -tree is 2x faster than FAST and FAIR B-tree because the leaf page size of B 3 -tree can be set to 8x larger than that of FAST and FAIR B-tree without degrading insertion performance. We also show that read transactions can access B 3 -tree without acquiring a shared lock because B 3 -tree remains always consistent while a sequence of 8-byte write operations are making changes to it. As a result, B 3 -tree provides high concurrency level comparable to FAST and FAIR B-tree.

24 February 2020 in IEEE Access
Verified
Journal Article
Open access
Younghoon KimYounghoon Kim
Younghoon Kim
JSJiwon Seo
Jiwon Seo
Social network services (SNSs) such as Twitter and Facebook have emerged as a new medium for communication. They offer a unique mechanism of sharing information by allowing users to receive all messages posted by those whom they “follow”. As information in today’s SNSs often spreads in the form of hashtags, detecting rapidly spreading hashtags in SNSs has recently attracted much attention. In this paper, we propose realistic epidemic models to describe the probabilistic process of hashtag propagation. Our models take into account the way how users communicate in SNSs; moreover the models consider the influence of external media and separate it from internal diffusion within networks. Based on the proposed models, we develop efficient inference algorithms that measure the propagation rates of hashtags in social networks. With real-life social network data including hashtags and synthetic data obtained by simulating information diffusion, we show that the proposed algorithms find fast-spreading hashtags more accurately than existing algorithms. Moreover, our in-depth case study demonstrates that our algorithms correctly find internal diffusion rates of hashtags as well as external media influences.

2 December 2022 in Briefings in Bioinformatics
Verified
Journal Article
Closed access
PDF file
KLKanggeun Lee
Kanggeun Lee
DCDongbin Cho
Dongbin Cho
JJJinho Jang
Jinho Jang
KCKang Choi
Kang Choi
HJHyoung-Oh Jeong
Hyoung-Oh Jeong
Semin LeeSemin Lee
Semin Lee
The accurate prediction of cancer drug sensitivity according to the multiomics profiles of individual patients is crucial for precision cancer medicine. However, the development of prediction models has been challenged by the complex crosstalk of input features and the resistance-dominant drug response information contained in public databases. In this study, we propose a novel multidrug response prediction framework, response-aware multitask prediction (RAMP), via a Bayesian neural network and restrict it by soft-supervised contrastive regularization. To utilize network embedding vectors as representation learning features for heterogeneous networks, we harness response-aware negative sampling, which applies cell line–drug response information to the training of network embeddings. RAMP overcomes the prediction accuracy limitation induced by the imbalance of trained response data based on the comprehensive selection and utilization of drug response features. When trained on the Genomics of Drug Sensitivity in Cancer dataset, RAMP achieved an area under the receiver operating characteristic curve > 89%, an area under the precision-recall curve > 59% and an $\textrm{F}_1$ score > 52% and outperformed previously developed methods on both balanced and imbalanced datasets. Furthermore, RAMP predicted many missing drug responses that were not included in the public databases. Our results showed that RAMP will be suitable for the high-throughput prediction of cancer drug sensitivity and will be useful for guiding cancer drug selection processes. The Python implementation for RAMP is available at https://github.com/hvcl/RAMP.

8 June 2025
Verified
Conference Paper
Open access
IHInyong Hwang
Inyong Hwang
DKDonghyeon Kim
Donghyeon Kim
SKSeokwon Kang
Seokwon Kang
TPTaehyeong Park
Taehyeong Park
TKTaehoon Kim
Taehoon Kim
YPYongjun Park
Yongjun Park

1 March 2019 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
PDF file
YWYoujip Won
Youjip Won
SKSundoo Kim
Sundoo Kim
JYJuseong Yun
Juseong Yun
DTDam Quang Tuan
Dam Quang Tuan
JSJiwon Seo
Jiwon Seo
In this work, we propose Database Shadowing, or DASH, which is a new crash recovery technique for SQLite DBMS. DASH is a hybrid mixture of classical shadow paging and logging. DASH addresses four major issues in the current SQLite journal modes: the performance and write amplification issues of the rollback mode and the storage space requirement and tail latency issues of the WAL mode. DASH exploits two unique characteristics of SQLite: the database files are small and the transactions are entirely serialized. DASH consists of three key ingredients Aggregate Update, Atomic Exchange and Version Reset. Aggregate Update eliminates the redundant write overhead and the requirement to maintain multiple snapshots both of which are inherent in the out-of-place update. Atomic Exchange resolves the overhead of updating the locations of individual database pages exploiting order-preserving nature of the metadata update operation in modern filesystem. Version Reset makes the result of the Atomic Exchange durable without relying on expensive filesystem journaling. The salient aspect of DASH lies in its simplicity and compatibility with the legacy. DASH does not require any modifications in the underlying filesystem or the database organization. It requires only 451 LOC to implement. In Cyclomatic Complexity score, which represents software complexity, DASH renders 33% lower (simpler) mark than PERSIST and WAL modes of SQLite. We implement DASH for SQLite on Android and extensively evaluate it on widely used smartphone devices. DASH yields 4x performance gain over PERSIST mode (default journaling mode). Compared to WAL mode (the fastest journaling mode), DASH uses only 2.5% of the storage space on average. The transaction latency of DASH at 99.9% is one fourth of that of WAL mode.