A Conditional Diffusion Transformer recovers full MIMO-OFDM channels from sparse noisy pilots, delivering over 5 dB gain versus baselines even at 1/32 pilot density and completing inference in 10 steps.
Analogical learning for cross- scenario generalization: Framework and application to intelligent lo- calization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Coupler is a domain-interleaved neural architecture for parameter-efficient representation learning of wireless channel state information across multiple physical domains.
GCD extracts approximate geometric channel features from coarse scenario maps using ray tracing and neighborhood search, converts them to pseudo-channels via feature alignment, and fuses them with partial pilot estimates in a neural network to obtain complete CSI.
AC²P²SL pipelines communication and computation across micro-batches in split learning, jointly optimizes splits and pre-allocation under constraints, and adds adaptive re-allocation for dynamic UEs to reduce overall training time.
citing papers explorer
-
Diffusion Inpainting MIMO-OFDM Channels with Limited Noisy Observations
A Conditional Diffusion Transformer recovers full MIMO-OFDM channels from sparse noisy pilots, delivering over 5 dB gain versus baselines even at 1/32 pilot density and completing inference in 10 steps.
-
Full-Domain Coupler: A Wireless Native Neural Backbone for Channel Representation and Deduction
Coupler is a domain-interleaved neural architecture for parameter-efficient representation learning of wireless channel state information across multiple physical domains.
-
Geometry-Aided Channel Deduction: A Robust Channel Acquisition Framework Utilizing Coarse Scenario Prompt
GCD extracts approximate geometric channel features from coarse scenario maps using ray tracing and neighborhood search, converts them to pseudo-channels via feature alignment, and fuses them with partial pilot estimates in a neural network to obtain complete CSI.
-
AC$^2$P$^2$SL: Adaptive Communication-Computation Pipeline Parallel Split Learning over Edge Networks
AC²P²SL pipelines communication and computation across micro-batches in split learning, jointly optimizes splits and pre-allocation under constraints, and adds adaptive re-allocation for dynamic UEs to reduce overall training time.