Member image
Kyeongha Rho
노경하
Ph.D. Candidate
School of Electrical Engineering, KAIST

About me

I am a second-year Ph.D. student at KAIST, where I also earned my M.S., advised by Professor Joon Son Chung. My research aims to learn semantically rich representations from multiple modalities (including vision, text and audio) and harness them to solve multimodal downstream tasks across perception and generation.

Education

Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea

Sep. 2024 - Present

Ph.D. in Electrical Engineering (Advisor: Joon Son Chung)

Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea

Sep. 2022 - Aug. 2024

M.S. in Electrical Engineering (Advisor: Joon Son Chung)

Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea

Mar. 2015 - Feb. 2019

B.S. in Electrical Engineering (Magna Cum Laude)

Work Experience

Naver Webtoon, Republic of Korea

Jul. 2022 - Aug. 2022

AI Research Intern (Advisor: Seungkwon Kim)

Agency for Defense Development (ADD), Republic of Korea

Jun. 2019 - May. 2022

Research Officer (Military Service; Discharged as First Lieutenant, Republic of Korea Army. Advisor: Youngjung Kim)

Data Intelligence Lab in KAIST, Republic of Korea

Mar. 2018 - Dec. 2018

Research Assistant (Advisor: Steven Euijong Whang)

Publications

2026

Thumbnail
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
Chaeyong Jung*, Kyeongha Rho*, Joon Son Chung
Preprint
Paper
Thumbnail
Inference-Time Scaling for Joint Audio–Video Generation
Jaemin Jung, Kyeongha Rho, Inkyu Shin, Joon Son Chung
Transactions on Machine Learning Research (TMLR)
Paper Project Page Code

2025

Thumbnail
MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning
Kyeongha Rho*, Hyeongkeun Lee*, Jae Won Cho, Joon Son Chung
Preprint
Paper
Thumbnail
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
Kyeongha Rho*, Hyeongkeun Lee*, Valentio Iverson, Joon Son Chung
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Paper Code

2024

Thumbnail
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
Jongsuk Kim*, Hyeongkeun Lee*, Kyeongha Rho*, Junmo Kim, Joon Son Chung
International Conference on Machine Learning (ICML)
Paper Code
Thumbnail
TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning
Chaeyoung Jung*, Suyeon Lee*, Kihyun Nam, Kyeongha Rho, You Jin Kim, Youngjoon Jang, Joon Son Chung
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Paper Code

2023

Thumbnail
That's What I Said: Fully-Controllable Talking Face Generation
Youngjoon Jang*, Kyeongha Rho*, Jongbin Woo, Hyeongkeun Lee, Jihwan Park, Youshin Lim, Byeong-Yeol Kim, Joon Son Chung
ACM International Conference on Multimedia (ACMMM)
Paper Project Page

2022

Thumbnail
Guideformer: Transformers for image guided depth completion
Kyeongha Rho*, Jinsung Ha*, Youngjung Kim
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Paper
Thumbnail
Action-driven contrastive representation for reinforcement learning
Minbeom Kim, Kyeongha Rho, Yong-duk Kim, Kyomin Jung
Plos one (IF=3.7)
Paper

Honors and Awards

Presidential Science Scholarship

2025

Outstanding Teaching Assistant Award

2024

Kwon Young-Se Scholarship

2022

4th Place, NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image (CVPR 2020 Workshop)

4th Place, NTIRE 2020 Challenge on Real Image Denoising (CVPR 2020 Workshop)

2020

Contact

  khrho325 (at) kaist.ac.kr
  Room 3103, N24 (LG Innovation Hall)
KAIST logo