channel-state-information

ARGUS is a passive Wi-Fi sensing system that uses attention-guided Transformers to identify people from Channel State Information without attached devices, achieving high accuracy with reduced computational cost.

CSI-JEPA is a self-supervised framework for learning reusable representations from unlabeled Wi-Fi channel state information, enabling label-efficient multi-task sensing. It achieves up to 98% label savings and outperforms supervised models.