Jisu Han

Hi, I'm Jisu! I am a first-year Ph.D. student in the Interdisciplinary Program in Artificial Intelligence (IPAI) at Seoul National University, and a member of the M.IN.D Lab, where I am fortunate to be advised by Taesup Moon.

I obtained my Master’s Degree in the Graduate School of AI at KAIST, in the Humanoid Generalization Lab directed by Beomjoon Kim. I received my Bachelor’s Degree in Computer Science from Ewha Womans University.

Mail  /  Github  /  LinkedIn  /  Google Scholar /  X

profile photo

My research interests lie in the intersection of robotics and machine learning. I am interested in developing foundation models for robotics that can generalize to new tasks and environments.

(* denotes equal contribution)

clean-usnob Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
Hongjoon Ahn*, Heewoong Choi*, Jisu Han*, Taesup Moon
Arxiv preprint 2025
Arxiv
clean-usnob Hierarchical and Modular Network on Non-prehensile Manipulation in General Environments
Yoonyoung Cho*, Junhyek Han*, Jisu Han, Beomjoon Kim
Robotics: Science and Systems (RSS), 2025
Paper / Project
clean-usnob Adaptive visual abstraction via object token merging and pruning for efficient robot manipulation
Jisu Han
CVPR Workshop (Causal and Object-Centric Representations for Robotics), 2024 Oral
Paper / Github
clean-usnob Preference learning for guiding the tree search in continuous POMDPs
Jiyong Ahn, Sanghyeon Son, Dongryung Lee, Jisu Han, Dongwon Son, and Beomjoon Kim.
Conference on Robot Learnining (CoRL), 2023
Paper / Video / Project / Github
clean-usnob WraspRobot: Bug-catching Robot
Jisu Han, Jaehoon Choi, Gunwoo Choi, and Dongwook Lee
Huggingface LeRobot WorldWide Hackerton, 2025 Top 10 Finalist among 3,000+ global participants
Huggingface Winner space / X
clean-usnob Clarifying the task: Identifying task from human videos as a representation
Jisu Han and Doohyun Lee
AI611: Machine Learning for Robotics (Prof. Joseph Lim) project, 2023
TL;DR To learn a generalized reward function that can be utilized on reinforcement learning, we devise a representation that can effectively disentangle environment information and task information.
Project
clean-usnob Cart MEME: Deep Learning Based Autonomous-Driving Cart
Jisu Han, Jiyoon Park, Chaewon Kim, and Sangsoo Park
Korea Information Processing Society (KIPS), 2021
Paper / Github
clean-usnob TheCodeEscape: VR room escape game based on Unity3D and Oculus
Jisu Han, Minyeong Hwang, and Seoungwoon Jung
KAIST MadCamp Final Project, 2019
Github / Demo

Workshop & Seminar

  • • CVPR Workshop (Causal and Object-Centric Representations for Robotics), 2024 - Oral Presentation
  • • KAIST AI Seminar Series, 2023

Research Experience
Sep 2024 - Nov 2024 Research Assistant, Cognitive Learning for Vision and Robotics Lab
Korea Advanced Institute of Science and Technology (KAIST)
• Research of analyzing the impact of data scaling on the performance of robotics policies
July 2021 - Aug 2022 Research Intern, Intelligent Mobile Manipulation Lab
Korea Advanced Institute of Science and Technology (KAIST)
• Research on interactive perception
Dec 2020 - Aug 2021 Research Intern, Dynamic Robotic Systems (DYROS) Lab
Seoul National University
• Developed a deep learning based grasp solution, published a domestic paper
May 2019 - July 2019 Research Intern, Information Coding and Processing Lab
Ewha Womans University
• Developed a drowsy driving prevention system based on the driver's eye-tracking system using OpenCV.

Teaching Assistant
Fall 2025 M2608.002100 Advanced Deep Learning
Seoul National University (Prof. Taesup Moon)