Joonhyung Park

Postdoctoral research associate at Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST)

I’m a Postdoctoral Research Associate at the Machine Learning and Intelligence Lab (MLILAB) in KAIST, where I received my Ph.D. degree advised by Prof. Eunho Yang. During my Ph.D., I worked as a research intern at Amazon AWS AI (GUI Agent team) and collaborated closely with Peng Tang, a researcher at Meta. I also worked with Prof. Sung Ju Hwang and Prof. Jinwoo Shin through collaborative research. I am a recipient of the Jang Young Sil Postdoctoral Fellowship, which supports outstanding postdoctoral researchers in Korea.

I am broadly interested in advancing the reasoning capabilities of AI models (System 2 Thinking) in the context of multi-modal learning. In particular, my recent research focuses on test-time scaling, pushing models toward deeper visual understanding and generation, and augmenting them with structured knowledge so that their learned representations are ready for in-depth reasoning. Ultimately, my research aims to design models capable of human-level reasoning by flexibly engaging with diverse modalities. Before the LLM era, I worked on modeling complex modalities through the lens of graph-structured knowledge - e.g. object graphs (3D vision), scene graphs (video) - revisiting real-world problems to provide structured and compositional understanding to machine learning models.

News

Aug 2025: Attending ACL 2025 in person. See you in Vienna!
Jul 2025: Gave a talk at Seoul AI Hub.
May 2025: One paper accepted to ACL 2025.
May 2025: Received Jang Young Sil Postdoctoral Fellowship from KAIST.
Dec 2024: Successfully defended Ph.D. dissertation (Committee: Eunho Yang, Jinwoo Shin, Jaegul Choo, Sung Ju Hwang, Jong Chul Ye).
Dec 2024 One paper is got accpeted to the AAAI 2025.
Jun 2024 Started Applied Scientist II Internship at Amazon AWS AI Labs.
May 2024 One paper accepted to ICML 2024.

Publications

  • R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding [paper]
    Joonhyung Park, Peng Tang, Sagnik Das, Srikar appalaraju, Kunwar Yashraj Singh, R. Manmatha, Shabnam Ghadar
    ACL 2025

  • PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency [paper]
    Yeonsung Jung, Heecheol Yun, Joonhyung Park, Jin-Hwa Kim, Eunho Yang
    ICML 2024

  • PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo Label [paper]
    Joonhyung Park, Hyujin Seo, Eunho Yang
    ICCV 2023

  • SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization [paper]
    Changhun Kim, Joonhyung Park, Hajin Shim, Eunho Yang
    INTERSPEECH 2023 (oral presentation) - Congrats on my mentee’s paper! :tada:

  • CALA: Connectivity- and Attribute-Aware Logit Adjustment for Class-Imbalanced Graphs
    Joonhyung Park*, Jaeyun Song*, Eunho Yang (* : equal contribution)
    TPAMI (Under Review)

  • WeavSpeech: Data Augmentation Strategy for Automatic Speech Recognition via Semantic-Aware Weaving [paper]
    Kyusung Seo, Joonhyung Park, Jaeyun Song, Eunho Yang
    ICASSP 2023 - Congrats on my mentee’s paper! :tada:

  • TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification [paper]
    Jaeyun Song*, Joonhyung Park*, Eunho Yang (*: equal contribution)
    ICML 2022

  • GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification [paper]
    Joonhyung Park*, Jaeyun Song*, Eunho Yang (*: equal contribution)
    ICLR 2022

  • Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing [paper]
    Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang, Eunho Yang
    AAAI 2022 (oral presentation, 380/9020=4.21%)

  • Graph Transplant: Node Saliency-Guided Graph mixup with Local Structure Preservation [paper]
    Joonhyung Park*, Hajin Shim*, Eunho Yang (*: equal contribution)
    AAAI 2022

Work Experience

  • Amazon AWS AI
    Applied Scientist II Intern
    Mentors: Peng Tang, Srikar Appalaraju, Yash Singh, Sagnik Das, and Shabnam Ghadar
    Jun 2024 – Nov 2024, Pasadena, CA

  • University of Virginia
    Research Intern
    Advisor: Prof. Homa Alemzadeh
    Jun 2018 – Aug 2018, Charlottesville, VA

  • Collaborative Robots Research Center, DGIST
    Research Intern
    Jun 2017 – Aug 2017, Daegu, South Korea

Education

  • Ph.D. (integrated) in Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2021 - Feb. 2025

  • M.S. in Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2020 - Mar. 2021

  • B.E. in Computer Science Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Mar. 2016 - Feb. 2020 - (Summa Cum Laude, 1st in Bachelor of Engineering)

Honors and Awards

  • Jang Young Sil Posdoctoral Fellowship (KRW 50 milion research grant), 2025
  • Hessel Leadership Award (DGIST President’s award for highest GPA), 2019
  • Dean’s List (top 3% academic scholarship), Spring 2018, Fall 2017, Spring 2017
  • DGIST Undergraduate Research Award, 2018

Mentoring

  • Sohee Kim (M.S. Student, KAIST → Ph.D. Student, KAIST)
    01.2023 - Current, Multimodal Reasoning: EMNLP 2025 (under review)
  • Hyunjin Seo (M.S. Student, KAIST → Ph.D. Student, KAIST)
    10.2022 - 06.2024, Graph Neural Networks: ICCV 2023, AAAI 2025
  • Changhun Kim (M.S. Student, KAIST → Research Scientist, AITRICS)
    08.2022 - 03.2023, Test-Time Adaptation: INTERSPEECH 2023 (oral)
  • Kyusung Seo (M.S. Student, KAIST → Research Engineer, LINE Plus)
    03.2022 - 10.2023, Semantic-aware Data Augmentation: ICASSP 2023

Academic Services

  • Conference Reviewer
    • International Conference on Machine Learning (ICML)
    • Neural Information Processing Systems (NeurIPS)
    • International Conference on Learning Representations (ICLR)
    • Computer Vision and Pattern Recognition (CVPR)
    • International Conference on Computer Vision (ICCV)
    • AAAI Conference on Artificial Intelligence (AAAI)
    • International Conference on Artificial Intelligence and Statistics (AISTATS)
    • International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
    • Learning on Graphs (LoG)
  • Journal Reviewer
    • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    • IEEE Transactions on Multimedia (TMM)
    • Knowledge and Information Systems

      Projects

  • Sub-task generation based point/regional Out-Of-Distribution detection, Samsung Electronics, Sep. 2020 - Sep. 2025
  • Predicting graph properties with few labels using Graph Neural Networks, Samsung Electronics, Sep. 2020 - Sep. 2025
  • Machine learning model for the prediction of Hypoxaemia during Endoscopic Retrograde Cholangiopancreatography, Yonsei Severance Hospital, Mar. 2020 - Jun. 2020