Scholar
Beomjoon Kim
Google Scholar ID: dw3rEwgAAAAJ
Korea Advanced Institute of Science & Technology (KAIST)
Citations & Impact
Citations
2,641
H-index
17
i10-index
19
Publications
20
Co-authors
20
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - PRESTO: Fast motion planning using diffusion models based on key-configuration environment representation (ICRA, 2025)
- - Prime the Search: Using Large Language Models for Guiding Geometric Task and Motion Planning by Warm-starting Tree Search (IJRR, 2025)
- - CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects (ICLR, 2024)
- - An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks (ICLR, 2024)
- - Open X-Embodiment: robotic learning datasets and RT-X models (ICRA, 2023)
- - Learning whole-body manipulation for quadrupedal robot (RA-L, 2023)
- - Preference learning for guiding the tree search in continuous POMDPs (CoRL, 2023)
- - Pre- and Post-Contact Policy Decomposition for Non-Prehensile Manipulation with Sim-to-Real Transfer (IROS, 2023)
- - Local object crop collision network for efficient simulation of non-convex objects in GPU-based simulators (RSS, 2023)
- - Ohm^2: Optimal hierarchical planner for object search in large environments via mobile manipulation (IROS, 2022)
- - Representation, learning, and planning algorithms for geometric task and motion planning (IJRR, 2021)
- - Integrated task and motion planning (Annual Review of Control, Robotics, and Autonomous Systems, 2021)
- - A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects (CoRL, 2021)
Research Experience
- - Directing the HuGe lab
- - Supervising multiple PhD, Masters, and intern students for their research work
Education
- - Ph.D. in Computer Science from MIT CSAIL
- - MSc in Computer Science from McGill University
- - BMath in Computer Science and Statistics from University of Waterloo
Background
- Beomjoon Kim is an Associate Professor in the Graduate School of AI at KAIST. He directs the Humanoid Generalization (HuGe) lab, where several research internship positions are available. His interest lies in creating general-purpose humanoids that can efficiently make decisions in complex environments.
Miscellany
- Links to CV, Google Scholar, Github, and Twitter provided on personal website
