LITE combines a 1D conv autoencoder for 50% CSI compression with an asymmetric SE-BiLSTM predictor to cut model complexity 83% and X-haul load while losing only 6% accuracy versus a full BiLSTM baseline.
Accurate channel prediction based on transformer: Making mobility negligible,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A hybrid CNN-KAN model with dual-domain and multi-scale frequency enhancement predicts CSI more accurately than RNN, LSTM, GRU, CNN, and Transformer baselines on QuaDRiGa simulations.
Adaptive 3D-RoPE adapts rotary positional encoding to wireless channel physics via learnable 3D frequencies and dynamic CSI control, yielding up to 10.7 dB NMSE gains in scale extrapolation and 1 dB in zero-shot tasks.
citing papers explorer
-
LITE: Lightweight Channel Gain Estimation with Reduced X-Haul CSI Signaling in O-RAN
LITE combines a 1D conv autoencoder for 50% CSI compression with an asymmetric SE-BiLSTM predictor to cut model complexity 83% and X-haul load while losing only 6% accuracy versus a full BiLSTM baseline.
-
ChannelKAN: Multi-Scale Dual-Domain Channel Prediction via Hybrid CNN-KAN Architecture
A hybrid CNN-KAN model with dual-domain and multi-scale frequency enhancement predicts CSI more accurately than RNN, LSTM, GRU, CNN, and Transformer baselines on QuaDRiGa simulations.
-
Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
Adaptive 3D-RoPE adapts rotary positional encoding to wireless channel physics via learnable 3D frequencies and dynamic CSI control, yielding up to 10.7 dB NMSE gains in scale extrapolation and 1 dB in zero-shot tasks.