From the 2 of 5 linked papers with an AI index.
5 papers
HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution
Taewoo Park, Kyeonghyun Yoo, Kiseok Kim +2
The paper introduces HALO, a runtime admission protocol that safely executes heterogeneous AI responses by checking each component’s prerequisites and re‑validating actions before…
Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation
Dohun Lee, Kyeonghyun Yoo, Seokmin Kim +3
The paper introduces Arm2Air, a method that transfers obstacle-avoidance motion skeletons learned from robot arms to UAVs for efficient 3D relay placement in cluttered urban enviro…
Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime
Taewoo Park, Kyeonghyun Yoo, Seunghyun Yoo +1
Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passage…
KD-EKF: Knowledge-Distilled Adaptive Covariance EKF for Robust UWB/PDR Indoor Localization
Kyeonghyun Yoo, Wooyong Jung, Namkyung Yoon +3
Ultra-wideband (UWB) indoor localization provides centimeter-level accuracy and low latency, but its measurement reliability degrades severely under Non-Line-of-Sight (NLOS) condit…
Beyond Learning: A Training-Free Alternative to Model Adaptation
Namkyung Yoon, Kyeonghyun Yoo, Wooyong Jung +2
Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-inten…