Jungsoo Park

Ph.D. Student, Georgia Tech

School of Interactive Computing

Coda S1153A

jpark3272 [AT] gatech.edu

About

Hello! I am a Ph.D. student in the School of Interactive Computing at Georgia Tech advised by Alan Ritter. I formerly worked as an applied scientist at Naver Clova, where I played a pivotal role in developing a foundational vision-language model: Hyperclova-X-Vision. Prior to Naver, I received B.E. in Statistics, B.S, and M.E. in Computer Science & Engineering from Korea University.

My research pursuits aim to create a comprehensive multimodal system capable of perceiving, comprehending, and reasoning. To achieve this goal, my research interests include aligning language and vision modalities and enhancing model comprehension of complex structural visual information. Building on this development, I am interested in applying such a multimodal system to expedite scientific discoveries.

News

Education

Georgia Institute of Technology Atlanta, GA, USA

Ph.D. in Computer Science Aug. 2024 - Present

Advisor: Alan Ritter

Korea University Seoul, Korea

M.E. in Computer Science & Engineering Mar. 2019 - Aug. 2021

Advisor: Jaewoo Kang

Korea University Seoul, Korea

B.E. in Statistics, B.S. in Computer Science & Engineering Mar. 2013 - Feb. 2019

Magna Cum Laude

Research Experience

Georgia Institute of Technology Atlanta, GA, USA

Graduate Research Assistant (Ph.D.) Aug. 2024 - Present

Advisor: Alan Ritter

Naver Clova Seongnam, Korea

Applied Scientist Jul. 2021 - Aug. 2024

Research Intern July. 2020 - Dec. 2020

Hyperscale AI

University of Washington Seattle, WA, USA

Visiting Scholar (remote) Jan. 2021 - Jul. 2021

Mentor: Sewon Min Advisor: Hannaneh Hajishirzi, Luke Zettlemoyer

Korea University Seoul, Korea

Graduate Research Assistant (M.E.) Mar. 2019 - Aug. 2021

Advisor: Jaewoo Kang

Publications

* indicates equal contribution.

Optimizing Test-Time Query Representations for Dense Retrieval

Mujeen Sung, Jungsoo Park, Jaewoo Kang, Danqi Chen, Jinhyuk Lee

Empirical Methods in Natural Language Processing-Findings

Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification

Jimin Hong*, Jungsoo Park*, Daeyoung Kim*, Seongjae Choi, Bokyung Son, Jaewook Kang

arXiv preprint

FaVIQ: FAct Verification from Information-seeking Questions

Jungsoo Park*, Sewon Min*, Jaewoo Kang, Luke Zettlemoyer, Hannaneh Hajishirzi

Association for Computational Linguistics

Consistency Training with Virtual Adversarial Discrete Perturbation

Jungsoo Park*, Gyuwan Kim*, Jaewoo Kang

North American Chapter of the ACL

Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

Gangwoo Kim, Hyunjae Kim, Jungsoo Park, Jaewoo Kang

Association for Computational Linguistics

Adversarial Subword Regularization for Robust Neural Machine Translation

Jungsoo Park, Mujeen Sung, Jinhyuk Lee, Jaewoo Kang

Empirical Methods in Natural Language Processing-Findings

Vitæ

Full CV in PDF.

  • Georgia Tech Aug. 2024 - Present
    Ph.D. in Computer Science
    Advisor: Alan Ritter
  • Naver Clova Jul. 2021 - Aug. 2024
    Applied Scientist
    Hyperscale AI
  • University of Washington Jan. 2021 - Aug. 2021
    Visiting Scholar (remote)
    Mentor: Sewon Min Advisors: Hannaneh Hajishirzi, Luke Zettlemoyer
  • Naver Clova Jul. 2020 - Dec. 2020
    Research Intern
    Language Research
  • Korea University Feb. 2019 - Aug. 2021
    M.E. in Software Engineering
    DMIS Lab
  • Republic of Korea Air Force Apr. 2014 - Apr. 2016
    Honorably discharged as Sergeant
    Compulsory military service
  • Korea University Mar. 2013 - Feb. 2019
    B.E. in Statistics & B.S. in Computer Science & Engineering
    Magna Cum Laude