Chae Won Kim

I am a Ph.D. student at the Electrical Engineering Department, Korea Advanced Institute of Science and Technology (KAIST) researching at the Integrated Vision & Language Lab, advised by Professor Yong Man Ro. I’m interested in multimodal learning, especially human multimodal tasks and vision-language models.

Publications

2024

• Phantom of Latent for Large Language and Vision Models

    Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro
    Preparation for ICLR 2025 [paper] | [code]

• TroL: Traversal of Layers for Large Language and Vision Models

    Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro
    Empirical Methods in Natural Language Processing (EMNLP), 2024 [paper] | [code]

• Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

    Byung-Kwan Lee, Chae Won Kim, Beomchan Park, Yong Man Ro
    Preparation for NeurIPS 2024 [paper] | [code]

• MoAI: Mixture of All Intelligence for Large Language and Vision Models

    Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro
    European Conference on Computer Vision (ECCV), 2024 [paper] | [code]

• CoLLaVO: Crayon Large Language and Vision mOdel

    Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro
    Findings of the Association for Computational Linguistics (ACL), 2024 [paper] | [code]

• Let’s Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

    Se Jin Park*, Chae Won Kim*, Hyeongseop Rha, Minsu Kim, Joanna Hong, Jeonghun Yeo, Yong Man Ro     Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) Oral, 2024
    🏆Received Outstanding Paper Award
    [paper] | [data] | [demo]

• Persona Extraction Through Semantic Similarity for Emotional Support Conversation Generation

    Seunghee Han, Se Jin Park, Chae Won Kim, Yong Man Ro
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 [paper]

2023

• Deep visual forced alignment: learning to align transcription with talking face video

    Minsu Kim, Chae Won Kim, Yong Man Ro
    AAAI Conference on Artificial Intelligence (AAAI), 2023 [paper]

Education

• Korea Advanced Institute of Science and Technology (KAIST), South Korea (2023 - Present)
   Ph.D in Electrical Engineering (advisor: Prof. Yong Man Ro)

• Korea Advanced Institute of Science and Technology (KAIST), South Korea (2021 - 2023)
   M.S in Electrical Engineering (advisor: Prof. Yong Man Ro)

• Korea Advanced Institute of Science and Technology (KAIST), South Korea (2016 - 2021)
   B.S in Electrical Engineering & Computer Science

• George Walton Comprehensive High School, U.S. (2012 - 2016)

Work Experience

• Software Intern at Samsung Electronics
   Jan 2021 - Feb 2021

• Engineer Intern at SK Hynix
   Jun 2019 - Aug 2019

Teaching Experience

• EE474 Introduction to Multimedia, KAIST (2024 Spring)
• EE305 Introduction to Electronics Design Lab, KAIST (2023 Fall)