Open access
Aug 2026
Channel Gains to Captions: Task-Unified Multi-Level RF Sensing With Vision–Language Models
A generative formulation for RF sensing, where millimeter-wave/terahertz channel gains are mapped to captions describing multi-level environmental semantics, and this framework achieves superior performance with a broader semantic scope, and enables task-unified sensing beyond predefined tasks.
Tian-Yu Hu, Zhi-Ren Gong, Hao-Wei Cui et al.
· IEEE Wireless Communications... · 0 citations