Sinjae Kang

Hi, I'm a student in Electrical Engineering at KAIST, where I am fortunate to be advised by Prof. Kimin Lee.

My long-term goal is to develop autonomous agents that can design and build complex physical systems. I explore how to build robot policies that learn from experience, and how to evaluate the quality of their behavior to guide continued improvement.

I am also grateful to be advised by Seonghyeon Ye and mentored by Kaixin Wang and Li Zhao at Microsoft Research.

Google Scholar  |  GitHub  |  LinkedIn  |  X (Twitter)  |  Email

profile photo
Education
  • Korea Advanced Institute of Science and Technology (KAIST),  2020 – Present
    B.S. in Electrical Engineering (Major), Computer Science (Minor)
    • GPA: 4.06 / 4.3 (Major: 4.12 / 4.3)
    • Served as President of the KAIST EE Student Council (2022)
    • Including mandatory military service (2023 – 2025)
Publications* indicates equal contribution
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li Zhao, Seonghyeon Ye^, Kimin Lee^
Under review, 2026
project website paper (arxiv)
WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
SPIGMw @ ICML, 2026
project website paper (arxiv) code (BC) code (RL)
Fatigue Injection: Exposing Hidden Physical Costs via Data Poisoning in Data-Driven Robot Learning
Under review, 2026
paper (arxiv)
EDITH: Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction
HRDw @ IROS, 2026
project website paper (arxiv)
Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation
Xinyao Qin, Junjie Lu, Kaixin Wang, Chuheng Zhang, Sinjae Kang, Kimin Lee, Min Xu, Bin Liang, Jun Yang, Li Zhao
Conference on Robot Learning (CoRL), 2026
paper (arxiv) video
Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
Haeone Lee, Taywon Min, Junsu Kim, Sinjae Kang, Fangchen Liu, Lerrel Pinto, Kimin Lee
IEEE International Conference on Robotics and Automation (ICRA), 2026
paper (arxiv)
Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback
Yongjin Yang*, Sinjae Kang*, Juyong Lee, Dongjun Lee, Se-Young Yun^, Kimin Lee^
arXiv preprint, 2025
paper (arxiv)
Research Experiences
  • Research Intern, KAIST AI · RISE Lab (Advisor: Kimin Lee),  2025.03 – Present
  • Research Intern, KAIST AI · ALIN Lab (Advisor: Jinwoo Shin),  2022.12 – 2023.03
Honors & Awards
  • Presidential Science Scholarship (CS field),  2020 – Present
    • Korea's highest honor scholarship in the sciences, granted by the President
  • KFAS (Korea Foundation for Advanced Studies) Undergraduate Scholarship (人材林),  2023 – Present
  • KAIST Alumni Academic Scholarship,  2022 – Present
    • Received from Hyunggyu Lim, former President of Samsung Electronics
  • KAIST Insung Award,  2023
    • Recognized for excellence in academics and leadership