A site-specific transformer model learns to probe key portions of the self-interference channel with few measurements and then designs full-duplex beams that outperform explicit channel estimation in ray-tracing simulations.
Grid-free MIMO beam alignment through site-specific deep learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
eess.SP 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
SiFo pretrains a CSI feedback model on source sites and uses RSRP-based user matching to calibration memory for site-specific subspace guidance at target sites without parameter updates.
A site-specific Type-II codebook design infers UE-dependent beam subspaces from RSRP fingerprints to achieve Type-II-comparable CSI capture with substantially lower online overhead and UE complexity.
citing papers explorer
-
Site-Specific Beamforming for Full-Duplex Massive MIMO Systems via Implicit Channel Estimation
A site-specific transformer model learns to probe key portions of the self-interference channel with few measurements and then designs full-duplex beams that outperform explicit channel estimation in ray-tracing simulations.
-
SiFo: Wireless Foundation Model for Low-Overhead Site-Specific CSI Feedback
SiFo pretrains a CSI feedback model on source sites and uses RSRP-based user matching to calibration memory for site-specific subspace guidance at target sites without parameter updates.
-
Bridging Standardized Codebook and Site-Specific Beamforming: A Unified Limited-Feedback Framework
A site-specific Type-II codebook design infers UE-dependent beam subspaces from RSRP fingerprints to achieve Type-II-comparable CSI capture with substantially lower online overhead and UE complexity.