Eun Woo Im [ɯnu ɪm] (임은우, 任殷佑)

Hello World! and welcome to my academic website.

I am a Computer Science Ph.D. student at Arizona State University, advised by Prof. Vivek Gupta. My ultimate research goal is to construct a reliable multimodal super intelligence system that non-technicians can train any visual tasks with a few demonstrations, and contribute to its practical and ethically proper deployment in real world scenarios.

Prior to ASU, I obtained my M.S. in Artificial Intelligence (2023) and B.S. in Mathematics (2021) from Hanyang University in Seoul, Republic of Korea. At Hanyang, I was fortunate to have supervision of Prof. Tae Hyun Kim on computational photography and Prof. Jae Hong Seo on ML-based speech recognition and cryptology. I have internship experience at KIST, and will be joining Amazon this Fall.

If you have any inquiries, please feel free to reach me out by email.

eunwooim@asu.edu  /  GitHub  /  Google Scholar  /  LinkedIn  /  CV

photo taken at monument valley forrest gump point
Forrest Gump Point, Monument Valley, Utah

📰 News
  • 05/2026
    The following paper has been accepted to TMLR journal. Video Generation Models: A Survey of Post-Training and Alignment
    • 05/2026
      Excited to join Amazon as an Applied Scientist Intern.
    • 05/2026
      Recognized as an ICML Gold Reviewer (top 25%) with financial aid award.
    • 04/2026
      A new preprint is released. Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
    • 02/2026
      The following paper has been accepted to TPAMI journal (IF≈18.6, top 1%). Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
    • 01/2026
      The following paper has been accepted to ICLR 2026. Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
    • 02/2025
      The following paper has been accepted to CVPR 2025. VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models
    • 04/2024
      I will be joining Arizona State University as a Ph.D. student.
    • 02/2024
      The following paper has been accepted to CVPR 2024. Harnessing Meta-Learning for Improving Full-Frame Video Stabilization
    • 08/2023
      I defended my thesis and received the Master's degree from Hanyang University. Thank you for your support.
    • 08/2023
      The following paper has been accepted to CIKM 2023. Deep Variational Bayesian Modeling of Haze Degradation Process (Long Paper)

📚 Publications

First authored works, * equal contribution.

project image Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
 Eun Woo Im, Dhruv Madhwal, Vivek Gupta
arXiv / project page
project image Video Generation Models: A Survey of Post-Training and Alignment
Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni, Eun Woo Im, Mohammadmahdi Honarmand, Zeyu Wang, Juntong Song, Fei Du, Xilin Jiang, Kexin Zheng, Tianzhi Li, Fei Tao, Pooyan Fazli
TMLR 2026 / TechRxiv / project page
project image Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
Muhammad Kashif Ali, Eun Woo Im, Dongjin Kim, Tae Hyun Kim, Vivek Gupta, Haonan Luo, Tianrui Li
TPAMI 2026 / arXiv / code
project image Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
 Eun Woo Im, Muhammad Kashif Ali, Vivek Gupta
ICLR 2026 / arXiv / code / project page
project image VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
Chaoyu Li, Eun Woo Im, Pooyan Fazli
CVPR 2025 / arXiv / code / project page
project image Harnessing Meta-Learning for Improving Full-Frame Video Stabilization
Muhammad Kashif Ali, Eun Woo Im, Dongjin Kim, Tae Hyun Kim
CVPR 2024 / arXiv / code
project image Deep Variational Bayesian Modeling of Haze Degradation Process
 Eun Woo Im*, Junsung Shin*, Sungyong Baik, Tae Hyun Kim
CIKM 2023 / arXiv / code

❝ Favorite Quotes