About Me

I am a PhD student in the Department of Electrical and Computer Engineering at Seoul National University, advised by Prof. Nam Ik Cho. I also work as an algorithm engineer at the Korean startup FuriosaAI.

Publications

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing
Wonjun Kang*, Kevin Galim*, Hyung Il Koo
European Conference on Computer Vision 2024 (ECCV 2024)
[Paper] [Code]

Counting Guidance for High Fidelity Text-to-Image Synthesis
Wonjun Kang*, Kevin Galim*, Hyung Il Koo, Nam Ik Cho
Winter Conference on Applications of Computer Vision 2025 (WACV 2025, Oral)
[Paper] [Code]

Can MLLMs Perform Text-to-Image In-Context Learning?
Yuchen Zeng*, Wonjun Kang*, Yicong Chen, Hyung Il Koo, Kangwook Lee
2024 Conference on Language Modeling (COLM 2024)
[Paper] [Code]

In-batch Ensemble Drafting: Robust Speculative Decoding for LVLMs
Minjae Lee*, Wonjun Kang*, Byeongkeun Ahn, Christian Classen, Minghao Yan, Hyung Il Koo, Kangwook Lee
2025 International Conference on Learning Representations SCOPE Workshop (ICLR 2025 Workshop)
[Paper]

Parameter-Efficient Fine-Tuning of State Space Models
Kevin Galim*, Wonjun Kang*, Yuchen Zeng*, Hyung Il Koo, Kangwook Lee
Neural Information Processing Systems 2024 FITML Workshop (NeurIPS 2024 Workshop, Oral)
[Paper] [Code]

TabFlex: Scaling Tabular Learning to Millions with Linear Attention
Yuchen Zeng, Wonjun Kang, Andreas Mueller
Neural Information Processing Systems 2024 TRL Workshop (NeurIPS 2024 Workshop)
[Paper]

Work Experience

FuriosaAI, June 2021 ~ Present
Algorithm Engineer

Education

Seoul National University, Mar 2020 ~ Present
Ph.D. in Electrical and Computer Engineering

Seoul National University, Mar 2014 ~ Feb 2020 (Military leave: 2.5 years)
B.S. in Electrical and Computer Engineering - GPA: 4.00/4.30 (Summa Cum Laude)

Seoul Science High School, Mar 2011 ~ Feb 2014
High School