Self-Localizing MIMO Beam Mapping for Intelligent Open RAN with Continuously Evolving Channel Memory

Open and intelligent radio access networks (RANs) envisioned for 6G require accurate and reusable wireless channel knowledge for intelligent inference and control. However, full-dimensional channel state information (CSI) and accurate location labels are difficult to acquire and maintain across open and multi-vendor deployments. This paper develops a self-localizing multiple-input multiple-output (MIMO) beam map framework that constructs a hierarchical wireless memory from highly sparse CSI measurements without explicit location labels. To reduce acquisition and processing overhead, we use beam-domain received signal strength (RSS) as compact inputs and theoretically show that they enable asymptotically unbiased spatial signature estimation. A dual-scale extractor captures intra-snapshot angular dependencies and inter-sample correlations for incomplete observations, and a hybrid temporal encoder is designed to consolidate recent CSI into stable short-term context for physical anchor inference. The inferred anchors spatially index a physically structured radio map embedding that stores long-term channel knowledge, which conditions a diffusion decoder for location-consistent full CSI reconstruction. Such a radio map embedding provides a persistent wireless knowledge representation that can be continuously updated and reused by intelligent RAN functions without repeated full CSI acquisition. Experiments demonstrate that the proposed framework improves physical-anchor recovery accuracy by over 30% under sparse measurements and achieves more than 20% channel-capacity gain in non-line-of-sight (NLOS) beam tracking over Kalman-filter-based baselines.