Dawit Mureja Argaw

Welcome! I recently completed my Ph.D. in Electrical Engineering at KAIST (Korea Advanced Institute of Science and Technology), where I was co-advised by Prof. Joon Son Chung and Prof. In So Kweon. I also received my B.S. in Electrical Engineering from KAIST. During my Ph.D., I gained valuable research experience through internships at NVIDIA (Santa Clara, CA), Adobe Research (San Jose, CA; twice), and KAUST. I am currently a recipient of the prestigious Jang Young Sil Postdoctoral Fellowship.

My research focuses on multimodal video understanding and efficient generative modeling, particularly for long-form media content.

Download CV LinkedIn Google Scholar Email

News & Updates

Apr. 2025: I will be joining Netflix (Los Gatos, CA) as a Research Scientist starting in August 2025. Thrilled to begin this next chapter!
Mar. 2025: I started my postdoctoral research at the Multimodal AI Lab, KAIST, under the supervision of Prof. Joon Son Chung.
Feb. 2025: I received the prestigious Jang Young Sil Postdoctoral Fellowship.
Jan. 2025: Our paper "High-Quality Joint Image and Video Tokenization with Causal VAE" was accepted to ICLR 2025. Excited to present!
Nov. 2024: Successfully defended my Ph.D. dissertation titled "Deep Long-form Video Understanding".

Publications

ICLR 2025

High-Quality Joint Image and Video Tokenization with Causal VAE

Dawit Mureja Argaw, Xian Liu, Qinsheng Zhang, Joon Son Chung, Ming-Yu Liu, Fitsum Reda

International Conference on Learning Representations, 2025

[PDF] [Code]

CVPR 2024

Scaling Up Video Summarization Pretraining with Large Language Models

Dawit Mureja Argaw, Seunghyun Yoon, Fabian Caba Heilbron, Hanieh Deilamsalehy, Trung Bui, Zhaowen Wang, Franck Dernoncourt, Joon Son Chung

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

[PDF] [Code]

CVPR 2024

Towards Automated Movie Trailer Generation

Dawit Mureja Argaw, Mattia Soldan, Alejandro Pardo, Chen Zhao, Fabian Caba Heilbron, Joon Son Chung, Bernard Ghanem

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

[PDF] [Code]

ICCV 2023

Long-range Multimodal Pretraining for Movie Understanding

Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson, In So Kweon, Fabian Caba Heilbron

International Conference on Computer Vision, 2023

[PDF] [Code]

ECCV 2022

The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing

Dawit Mureja Argaw, Fabian Caba Heilbron, Joon-Young Lee, Markus Woodson, In So Kweon

European Conference on Computer Vision, 2022

[PDF] [Code]

CVPR 2022

Long-term Video Frame Interpolation via Feature Propagation

Dawit Mureja Argaw, In So Kweon

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

[PDF] [Code]

AAAI 2021

Motion-blurred Video Interpolation and Extrapolation

Dawit Mureja Argaw, Junsik Kim, Francois Rameau, In So Kweon

Association for the Advancement of Artificial Intelligence, 2021

[PDF] [Code]

AAAI 2021

Optical Flow Estimation from a Single Motion-blurred Image

Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Jae Won Cho, In So Kweon

Association for the Advancement of Artificial Intelligence, 2021

[PDF] [Code] (Invited poster presentation at "What is Motion For?" Workshop @ ECCV 2022)

WACV 2024

Blurry Video Compression: A Trade-off between Visual Enhancement and Data Compression

Dawit Mureja Argaw, Junsik Kim, In So Kweon

IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

[PDF] [Code]

CVPRW 2021

Restoration of Video Frames from a Single Blurred Image with Motion Understanding

Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Chaoning Zhang, In So Kweon

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021

[PDF] [Code] (Oral Presentation)

See my Google Scholar for a full publication list.

Awards and Honors

2025: Jang Young Sil Postdoctoral Fellowship, KAIST
2024: Top Weights and Biases User (>800K hours tracked in 2024), Weights & Biases
2023: Top Reviewer Award, Conference on Neural Information Processing Systems (NeurIPS)
2023: Outstanding Reviewer Award, International Conference on Computer Vision (ICCV)
2022: Best Poster Award, "What is Motion For?" (WiMF) Workshop at ECCV 2022
2022: ECCV Travel Grant, European Conference on Computer Vision (ECCV)
2022: Outstanding Reviewer Award, European Conference on Computer Vision (ECCV)
2022: CVPR Travel Grant, Conference on Computer Vision and Pattern Recognition(CVPR)
2021: Finalist, Qualcomm Innovation Fellowship Korea
2018: Magna Cum Laude, KAIST Electrical Engineering Department
2014-2024: Full Scholarship Recipient for B.S. and Integrated M.S./Ph.D. Program, KAIST

Academic Services

Journal Reviewer:
- Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Conference Reviewer:
- Machine Learning: ICML(2024-2025), ICLR (2024-2025), NeurIPS (2023-2025)
- Computer Vision: CVPR (2022-2025), ICCV (2021, 2023, 2025), ECCV (2022, 2024)
Student Volunteer: ICLR (2020), ICML (2020), NeurIPS (2020)