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.

  • Multimodal Large Language Models Reasoning: Generation and Comprehension
  • Graphical User Interface (GUI) Agent
  • Graph-driven Compositional Modal Understanding

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 (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

  • Applied Scientist II Intern, Amazon AWS AI, Pasadena, CA, Jun. 2024 -
    • Mentors: Peng Tang, Srikar Appalaraju, Yash Singh, Sagnik Das, and Shabnam Ghadar
  • Research Intern, University of Virginia, Charlottesville, VA, Jun. 2018 - Aug. 2018
    • Advisor: Prof. Homa Alemzadeh
    • Medical concept extraction in text data for Cognitive Assistant System of emergency medical response (supported by the National Institute of Standards and Technology).
  • Research Intern, Collaborative Robots Research Center, DGIST, Daegu, Jun. 2017 - Aug. 2017
    • Development of treadmill for stroke hemiplegic patients

Education

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

  • 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 College of Engineering)

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

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
    • Transactions on Neural Networks and Learning Systems (TNNLS)
    • Transactions on Multimedia (TMM)