CRS-LLM reformulates cooperative mmWave beam tracking as joint BS-beam classification using a dual-view CSI tokenizer, truncated GPT backbone, and switch-gated predictor, reporting higher Top-1 accuracy than baselines in simulations.
6G wireless networks: Vision, requirements, architecture, and key technologies,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SP 2years
2026 2representative citing papers
citing papers explorer
-
CRS-LLM: Cooperative Beam Prediction with a GPT-Style Backbone and Switch-Gated Fusion
CRS-LLM reformulates cooperative mmWave beam tracking as joint BS-beam classification using a dual-view CSI tokenizer, truncated GPT backbone, and switch-gated predictor, reporting higher Top-1 accuracy than baselines in simulations.
- Array Zooming Optimization for Near-Field Localization With Movable Antennas