Context-Aware Iterative Token Detection and Masked Transmission for Wireless Token Communication
This work addresses efficient wireless communication for token-based systems, offering incremental improvements in transmission rate and quality.
The paper tackled the problem of improving wireless token communication by proposing a context-aware framework that uses a pretrained masked language model for joint token detection and masking. The result was a substantial improvement in reconstructed sentence quality and effective rate adaptation under various channel conditions.
The success of large-scale language models has established tokens as compact and meaningful units for natural-language representation, which motivates token communication over wireless channels, where tokens are considered fundamental units for wireless transmission. We propose a context-aware token communication framework that uses a pretrained masked language model (MLM) as a shared contextual probability model between the transmitter (Tx) and receiver (Rx). At Rx, we develop an iterative token detection method that jointly exploits MLM-guided contextual priors and channel observations based on a Bayesian perspective. At Tx, we additionally introduce a context-aware masking strategy which skips highly predictable token transmission to reduce transmission rate. Simulation results demonstrate that the proposed framework substantially improves reconstructed sentence quality and supports effective rate adaptation under various channel conditions.