Yunseok Jang
Scholar

Yunseok Jang

Google Scholar ID: YvYBeysAAAAJ
University of Michigan, Ann Arbor
Machine LearningComputer VisionVideo Understanding
Citations & Impact
All-time
Citations
1,170
 
H-index
8
 
i10-index
8
 
Publications
16
 
Co-authors
26
list available
Resume (English only)
Academic Achievements
  • Published 'Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents' at CVPR 2025
  • Published 'YTCommentQA: Video Question Answerability in Instructional Videos' at AAAI 2024
  • Published 'Multimodal Subtask Graph Generation from Instructional Videos' at ICLR Workshop on Multimodal Representation Learning 2023
  • Published 'RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects' at CVPR Workshop on AI for Content Creation 2022 (Best Paper Award - Runner up)
  • Published 'Adversarial Defense via Learning to Generate Diverse Attacks' at ICCV 2019
  • Published 'Diversity-Sensitive Conditional Generative Adversarial Networks' at ICLR 2019
  • Published 'Video Prediction with Appearance and Motion Conditions' at ICML 2018
  • Published 'TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering' at CVPR 2017 (Spotlight); extended version accepted in IJCV vol.127, no.10, pp.1385–1412, October 2019
Research Experience
  • Research Scientist, Meta Superintelligence Labs, Menlo Park, CA (Aug. 2025 – Present), Manager: Lu Yuan
  • Research Intern, LG AI Research, Ann Arbor, MI (Nov. 2021 – May 2023)
  • Research Intern, Adobe Research, San Jose, CA (Jun. 2020 – Nov. 2020)
  • Research Intern, Google Research, Mountain View, CA (Jun. 2019 – Dec. 2019)
  • Visiting Scholar, University of Michigan, Ann Arbor, MI (Mar. 2018 – Jun. 2018), Advisor: Honglak Lee
  • Research Intern, Yahoo! Research, New York, NY (Jun. 2017 – Nov. 2017)
  • Software Engineer (iOS and Backend), KAKAO, Gyeonggi-do, Korea (Sep. 2012 – Jul. 2014)
  • Software Engineer (Android and Windows), ESTsoft, Seoul, Korea (Jan. 2011 – Aug. 2012)