Joohyun Chang

I am a first-year M.S. student at KAIST Advanced Machine Intelligence (AMI) Lab, affiliated with the School of Computing at Korea Advanced Institute of Science and Technology (KAIST), where I am advised by Prof. Tae-Hyun Oh. I received my bachelor’s degree at Kyung Hee University

My research interests include vision language models, multi-modal learning, and video question answering.

Contact Info: CV / Linkedin / Github

News

Sep 25, 2026	One paper has been accepted to NeurIPS 2026
Apr 07, 2026	One paper has been accepted to ACL 2026 as an Oral paper
Oct 31, 2025	One paper has been accepted to TPAMI (Impact Factor 18.6, JCR top 1.1%)
Aug 02, 2025	One paper has been accepted to BMVC 2025 as an Oral paper

Selected Publications

* Co-first authorship (equal contribution)
† Corresponding author

NeurIPS

FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling

Kim Sung-Bin, Joohyun Chang, David Harwath, and Tae-Hyun Oh^†

To appear in Advances in Neural Information Processing Systems , 2026

arXiv Bib Project Page

@inproceedings{sung2026facedit,
  title = {FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling},
  author = {Sung-Bin, Kim and Chang, Joohyun and Harwath, David and Oh, Tae-Hyun},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2026},
}

ACL

SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter

Lee Jung-Mok, Kim Sung-Bin, Joohyun Chang, Lee Hyun, and Tae-Hyun Oh^†

In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL) , 2026

* Accepted as a full oral paper (19% acceptance rate)

arXiv Bib Code Project Page

@inproceedings{wang2025ecomscriptbench,
  title = {SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter},
  author = {Jung-Mok, Lee and Sung-Bin, Kim and Chang, Joohyun and Hyun, Lee and Oh, Tae-Hyun},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics},
  year = {2026},
}

TPAMI

CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition

Jongseo Lee^*, Joohyun Chang^*, Dongho Lee, and Jinwoo Choi^†

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2026 (Impact Factor 18.6, JCR top 1.1%)

arXiv Bib Code

@article{lee2026ca2st,
  title = {CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition},
  author = {Lee, Jongseo and Chang, Joohyun and Lee, Dongho and Choi, Jinwoo},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {3},
  pages = {2803-2819},
}

BMVC

HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization

Joohyun Chang^*, Soyeon Hong^*, Hyogun Lee^*, Seong Jong Ha, Dongho Lee, Seong Tae Kim^†, and Jinwoo Choi^†

In The Thirty Sixth British Machine Vision Conference (BMVC) , 2025

* Accepted as a full oral paper (3.8% acceptance rate)

arXiv Bib Code Project Page

@inproceedings{chang2025herovql,
  title = {HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization},
  author = {Chang, Joohyun and Hong, Soyeon and Lee, Hyogun and Ha, Seong Jong and Lee, Dongho and Kim, Seong Tae and Choi, Jinwoo},
  booktitle = {The Thirty Sixth British Machine Vision Conference},
  year = {2025},
}

Honors & Awards

Best Paper Award (Honorable Mention), IPIU, 2025
Best Paper Award (Honorable Mention, Undergraduate), KCC, 2024
Achievement Scholarship, Anyang City Talent Nurture Foundation, 2024
Lee Min-young Alumni Scholarship, Kyunghee University, 2023 -- 2024

Education

M.S. in School of Computing, Korea Advanced Institute of Science and Technology (KAIST)

2025 -- Present
B.S. in Computer Science and Engineering, Kyung Hee University

2019 -- 2025

Experience

Undergraduate Research Intern, Vision and Learning Lab at Kyung Hee University

Advisor: Jinwoo Choi

2023 -- 2025

Office: Rm. 608, E3-5 (KRAFTON SoC Building), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea