YOCO: You Only Calibrate Once. Fast Mocap Calibration for Dexterous Teleoperation

This paper presents YOCO, a fast, few-shot, fine-tuning-free calibration framework for dexterous teleoperation. It corrects biased hand-pose streams using a small set of paired raw and target poses, conditioning a calibration HyperNet on these examples to predict LoRA-style updates for a frozen MANO hand-estimation module. YOCO improves calibration efficiency and teleoperation performance across synthetic and real-world datasets.