We adapt DINO-style self-supervised learning toWi-Fi channel state information (CSI) time-series data. Bytreating the subcarrier–time grid as a patchable signal andtraining a Vision Transformer (ViT) with student–teacher architecture, we learn RF embeddings that significantly improvedownstream decoding tasks over hand-crafted features. Ourmethod achieves superior linear-probe accuracy, produces wellclustered embedding geometries, and demonstrates strong dataefficiency across label … Continue reading DINO v2 for Self-Supervised RF Representations