Taeyoung Kim
Ph.D. Student
KAIST AI
taeyoungkim85 [AT] kaist.ac.kr
About
I am a second-year Ph.D. student at KAIST, advised by Jinwoo Shin. I received my B.S. degree in Computer Science / Electrical Engineering (double major) at KAIST in 2024. My research interest lies in robotics foundation models for general-purpose robot manipulation. Recently, I am interested in learning robust and transferable representations that enable robots to generalize across diverse tasks, embodiments, and environments.
Publications
(*: Equal Contribution, †: Equal Advising)
Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction
Taeyoung Kim, Junyoung Sung, Heeseung Kwon, Minseop Kim, Jinwoo Shin
Preprint
RLDX-1 Technical Report
Dongyoung Kim*§, Huiwon Jang*§, Myungkyu Koo*, Suhyeok Jang*, Taeyoung Kim*, et al., Jinwoo Shin§
Project Lead, Technical Report, 2026
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo†, Jinwoo Shin†
ICML 2026
HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
Myungkyu Koo*, Daewon Choi*, Taeyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo†, Jinwoo Shin†
ICLR 2026
Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction
Taeyoung Kim, Junyoung Sung, Heeseung Kwon, Minseop Kim, Jinwoo Shin
Preprint
PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models
Hojin Jeon, Jimin Lee, Taekwan Kim, Nayoung Oh, Taeyoung Kim, Myungkyu Koo, Jinmo Koo, Joonwoo Ahn, Jinwoo Shin
Preprint
Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs
Junhyeong Park, Wook Jung, Taeyoung Kim, Huiwon Jang, Jinwoo Shin
CoRL 2026 Workshop on Scaling Human2Robot
Oral Presentation
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models
Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo
CoRL 2026 Workshop on Pretrain to Adapt
FineAct: Coarse-to-Fine Vision-Language-Action Representation Alignment for Policy Learning
Wook Jung, Dongyoung Kim, John Won, Taeyoung Kim, Jinwoo Shin
Preprint
RLDX-1 Technical Report
Dongyoung Kim*§, Huiwon Jang*§, Myungkyu Koo*, Suhyeok Jang*, Taeyoung Kim*, et al., Jinwoo Shin§
Project Lead, Technical Report, 2026
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo†, Jinwoo Shin†
ICML 2026
HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
Myungkyu Koo*, Daewon Choi*, Taeyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo†, Jinwoo Shin†
ICLR 2026
Education
Korea Advanced Institute of Science and Technology (KAIST)Sep. 2024 - Present
Ph.D. Student in Artificial Intelligence
Advisor: Jinwoo Shin
Korea Advanced Institute of Science and Technology (KAIST)Mar. 2018 - Aug. 2024
B.S. in Computer Science and Electrical Engineering (double major)
Cum Laude
Experience
Honors and Awards
1st Place in Korean LLM Leaderboard, hyunseoki/ko-en-llama2-13bOct. 2023
National Science & Technology ScholarshipMar. 2018 - Feb. 2024
Academic Excellence Award (Dean's List)Jun. 2018
