SEMIKHORN: Globally balanced affinities for mmWave Localization in MU mMIMO systems
2026-06-08T08:51:44Z•d4ccf429824397e3c1af890a3681dc48f755dae6a9974463363b1c0c5942cc98
CNNCSI-feedbackCSI-fusionCsiCoGenResNetSEMIKHORNTHzUAVadaptive-beamformingbayesian-optimizationcompressed-feedbackdiffusion-modelsentropic-optimal-transportgenerative-modelslocalizationmMIMOmmWavemulti-UAVmulti-agent-RL','MARL'radio-mapsemi-supervised-learningsparse-array-designsuperimposed-pilotst-SNEkhornvariational-bayes
What happened
Collection of new academic works (arXiv 2026-06-08) on wireless communications, sensing, and learning for radio systems. Key contributions: SEMIKHORN — a semi-supervised mmWave localization pipeline using t-SNEkhorn and entropic optimal transport for globally balanced affinities and multi-BS CSI fusion (reported mean localization error ~6.86% within 100m using <15% labeled samples); a variational-Bayes algorithm for superimposed-pilot channel estimation in partially connected dual-wideband THz MU-MIMO; CNN- and ResNet-based deep learning methods for rapid sparse-array design and adaptive beam‑
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_eess_sp
- Record identifier
- d4ccf429824397e3c1af890a3681dc48f755dae6a9974463363b1c0c5942cc98
- Enrichment time
- 2026-06-08T08:51:44Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.