Joongheon Kim

Reaching high-frequency Fourier modes in quantum neural networks does not require deeper data re-uploading, but rather an exact algebraic placement of entangling gates that forces quantum states and observables to intersect on frequency-invariant operator planes.

Slashing closed-loop rollout time by up to 67% on complex parallel-mechanism robots, graph-native compilation replaces brittle, fragmented kinematics pipelines with a single virtual-work-preserving interface that runs natively across modern physics engines.

In imitation learning and adaptive Cartesian tracking (IL-ACT), a novel motion control framework for a 30-ton-class excavator, is proposed, with bounded adaptive states and Cartesian feedback, with reference admissibility conditional on governor feasibility.