Hi! I’m Yunseok Jang, a final-year Ph.D. candidate in Computer Science and Engineering at the University of Michigan, Ann Arbor (UMich), advised by Professor Honglak Lee. Prior to UMich, I was a master’s student in Computer Science and Engineering at Seoul National University, where I worked with Professor Gunhee Kim. My research interests lie in video understanding through deep learning. In particular, I focus on realistic video generation and the semantic interpretation of videos on the web.

Research Interests: Machine Learning, Multimodal Learning, Generative Models, Large Vision and Language Models

I am on the industry job market, and will start interviewing from early 2025!

Education

  • University of Michigan, Ann Arbor, MI (Sep. 2018 – May 2025)
    Ph.D. in Computer Science and Engineering
    Advisor: Honglak Lee
  • Seoul National University, Seoul, Korea (Mar. 2016 – Feb. 2018)
    M.S. in Computer Science and Engineering
    Advisor: Gunhee Kim
  • KAIST, Daejeon, Korea (Feb. 2007 – Aug. 2015)
    B.S. in Computer Science
    Cumulative Rank: 1st out of 231 students in August 2015

Selected Publications

For all papers, please visit my Google Scholar profile.


Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
Yunseok Jang*, Yeda Song*, Sungryull Sohn, Lajanugen Logeswaran, Tiange Luo, Dong-Ki Kim, Kyunghoon Bae, Honglak Lee
In CVPR, 2025

YTCommentQA: Video Question Answerability in Instructional Videos
Saelyne Yang, Sunghyun Park, Yunseok Jang, Moontae Lee
In AAAI, 2024
[PDF] [Dataset] [Poster]

Multimodal Subtask Graph Generation from Instructional Videos
Yunseok Jang*, Sungryull Sohn*, Lajanugen Logeswaran, Tiange Luo, Moontae Lee, Honglak Lee
In ICLR First Workshop on Multimodal Representation Learning, 2023
[PDF] [Slide] [Poster] [Video]

RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects
Yunseok Jang, Ruben Villegas, Jimei Yang, Duygu Ceylan, Xin Sun, Honglak Lee
In CVPR Workshop in AI for Content Creation, 2022
(Best Paper Award - Runner up)
[PDF] [Project] [Slide] [Poster]

Adversarial Defense via Learning to Generate Diverse Attacks
Yunseok Jang*, Tianchen Zhao*, Seunghoon Hong, Honglak Lee
In ICCV, 2019
[PDF] [Code] [Poster]

Diversity-Sensitive Conditional Generative Adversarial Networks
Dingdong Yang*, Seunghoon Hong*, Yunseok Jang, Tianchen Zhao, Honglak Lee
In ICLR, 2019
[PDF] [Project] [Code] [Poster] [Video]

Video Prediction with Appearance and Motion Conditions
Yunseok Jang, Gunhee Kim, Yale Song
In ICML, 2018
[PDF] [Project] [Slide] [Poster]

TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering
Yunseok Jang, Yale Song, Youngjae Yu, Youngjin Kim, Gunhee Kim
In CVPR, 2017 (Spotlight)
[PDF] [Code and Dataset] [Slide] [Poster] [Video]
A longer version is accepted in IJCV vol.127, no.10, pp.1385-1412, October 2019 [Link]

Professional Experiences

Professional Activities

Workflow Manager

  • ICML Workshop (2019)

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • Journal of Machine Learning Research (JMLR)

Conference Reviewer

  • CVPR (2019–2025)
  • ICCV/ECCV (2019–2023)
  • ICLR (2020–2024)
  • ICML (2021–2023)
  • NeurIPS (2020–2023)
  • AAAI (2021)
  • ICMI (2016–2018)

Honors and Awards

  • Recipient of OpenAI Researcher Access Program (Jul. 2024 – Dec. 2024)
  • Recipient of Kwanjeong Graduate Student Scholarship Program (Jul. 2018 – Dec. 2023)
  • CVPR 2022 AI for Content Creation Workshop Best Paper - Runner Up Award (Jun. 2022)
  • Outstanding Graduate Student Instructor Award in University of Michigan CSE (Jul. 2021)
  • ICML 2021 Best Reviewer Award (Jul. 2021)
  • ECCV 2020 Outstanding Reviewer Award (Aug. 2020)
    (Co-listed as one of the top 12 reviewers)
  • Best Thesis Award in SNU CSE (Feb. 2018)
  • Recipient of KFAS Graduate Student Scholarship Program (Mar. 2016 – Feb. 2018)
  • Preparatory Association Award for the highest GPA in KAIST (Feb. 2016)
  • Recipient of Fulbright & GE Foundation Scholar Leaders Program (Jun. 2008 – Aug. 2015)