Minjae Kang

I am a Ph.D. student at Robot Learning Lab in the Department of Electrical and Computer Engineering at Seoul National University, South Korea, advised by Prof. Songhwai Oh. I received my B.S. in Electrical and Computer Engineering from Seoul National University in 2019. My research focuses on vision-language models for robotics, with broader interests in reinforcement learning, imitation learning, lifelong learning, and skill discovery.

Highlighted Publications

• Playbook: Scalable Discrete Skill Discovery from Unstructured Datasets for Long-Horizon Decision-Making Problems

  Minjae Kang, Mineui Hong, and Songhwai Oh

  IEEE Robotics and Automation Letters (RA-L), Oct. 2025. PDF GIT

• Automatic Real-to-Sim-to-Real System through Iterative Interactions for Robust Robot Manipulation Policy Learning with Unseen Objects

  Minjae Kang, Hogun Kee, Hosung Lee, and Songhwai Oh

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2025. PDF GIT VIDEO

• Gradual Receptive Expansion Using Vision Transformer for Online 3D Bin Packing

  Minjae Kang, Hogun Kee, Yoseph Park, Junseok Kim, Jaeyeon Jeong, Geunje Cheon, Jaewon Lee, and Songhwai Oh

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2024. PDF VIDEO

• Object Rearrangement Planning for Target Retrieval in a Confined Space with Lateral View

  Minjae Kang, Junseok Kim, Hogun Kee, and Songhwai Oh

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2023. PDF VIDEO

• Grasp Planning for Occluded Objects in a Confined Space with Lateral View Using Monte Carlo Tree Search

  Minjae Kang, Hogun Kee, Junseok Kim, and Songhwai Oh

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2022. PDF VIDEO