Jeonghwan Kim
3 papers · Latest:
Robotics
LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts
LineRides is a novel line-guided reinforcement learning framework enabling a bicycle robot to learn diverse stunts without demonstrations.
2605.05110
RoboticsOmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
OmniRobotHome is a new multi-camera platform enabling real-time, occlusion-robust 3D tracking for multiadic human-robot interaction in home environments.
2604.28197
Computer VisionDeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
DeVI enables physics-based dexterous human-object interaction control using synthetic videos and a novel hybrid 2D/3D tracking reward.
2604.20841
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.