Null-space flow matching decomposes MIMO CSI estimation into direct range-space reconstruction from noisy pilots and iterative FM-based null-space generation, achieving competitive NMSE under a ~3 ms latency budget with a power-law schedule and noise-aware correction.
An asymptotically MSE- optimal estimator based on Gaussian mixture models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems
Null-space flow matching decomposes MIMO CSI estimation into direct range-space reconstruction from noisy pilots and iterative FM-based null-space generation, achieving competitive NMSE under a ~3 ms latency budget with a power-law schedule and noise-aware correction.