I am a master’s student in the Department of Computer Science and Engineering at Korea University, working in the Multimodal Interactive Intelligence Laboratory (MIIL) under the supervision of Prof. Paul Hongsuck Seo.

My research interests are in multimodal generative models, particularly diffusion-based approaches for audio-visual understanding and generation. I am broadly interested in exploring how different modalities can be aligned, fused, and generated through modern deep learning frameworks.

Education

• M.S. in Computer Science and Engineering, Korea University (Mar. 2025 – Present)
  • Advisor: Prof. Paul Hongsuck Seo
• B.S. in Computer Science and Engineering, Korea University (Mar. 2019 – Feb. 2025)

Experiences

• Research Intern, MIIL, Korea University (Jul. 2024 – Feb. 2025)
  • Advisor: Prof. Paul Hongsuck Seo
• Research Intern, AI Lab, Korea University (Jan. 2024 – Jun. 2024)
  • Advisor: Prof. Dongsuk Yook

Publications

• DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
  Geonyoung Lee^*, Geonhee Han^*, Paul Hongsuck Seo. Interspeech 2025. (* Equal contribution)

• Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
  Dohyun Kim^*, Sehwan Park^*, Geonhee Han, Seung Wook Kim, Paul Hongsuck Seo. CVPR 2025. (* Equal contribution)

• CycleDiffusion: Voice Conversion Using Cycle-Consistent Diffusion Models
  Dongsuk Yook, Geonhee Han, Hyung-Pil Chang, In-Chul Yoo. (2024). Applied Sciences, 14(20), 9595.

Honors and Awards

• Grand Prize, Yongin City SW/AI Hackathon (2023)
• 1st Place - Private Leaderboard, Dacon Twitter Sentiment Analysis Challenge (2023)

Teaching

• Teaching Assistant, COSE474 “Deep Learning”, Korea University (Spring 2025)
• Instructor, DLAB Coding Academy (Dec. 2022 – Feb. 2023)

Service and Leadership

• Sergeant, Republic of Korea Army (Apr. 2021 – Oct. 2022), honorably discharged
• President, Classical Guitar Club, Korea University (Jan. 2020 – Dec. 2020)