cs.AINov 13, 2026

Dual-Stage Channel-Posterior Integration for MLM-Aided Token Communications

Authors: Hyelin Nam, Jihoon Lee, Seung-Woo Ko, Jinho Choi, Seong-Lyun Kim

Organizations: School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea · Department of Smart Mobility Engineering, Inha University, Incheon, South Korea · School of Electrical and Mechanical Engineering, Adelaide University, Adelaide, Australia

Abstract

Token transmission over conventional digital modulation is vulnerable to channel impairments, leading to bit errors that cause received tokens to become contextually inconsistent. This paper proposes a receiver-side dual-stage channel-posterior integration framework for masked language model (MLM)-aided token reconstruction. In the proposed framework, the receiver detects unreliable token positions from channel reliability and constructs a vocabulary-level channel-posterior. In particular, within the receiver, Posterior-Weighted Input Embedding (PWE) injects this posterior into the MLM input, while Adaptive Output Logit Fusion (AOF) reuses it at the output with a channel-adaptive weight. Consequently, multiple unreliable tokens can be reconstructed in a single bidirectional MLM inference without retransmission, transmitter-side encoding, or additional MLM training. Experiments over noisy channels show up to a 67.267.2% improvement in cosine similarity over context-only MLM reconstruction, with consistent gains across different MLM architectures and existing language-model-aided methods.

Explore similar work

CardsList
  1. Context-Aware Wireless Token Communication via Joint Token Masking and Detection

    May 4, 2026Junyong Shin, Joohyuk Park, Yongjeong Oh +3

  2. Token Encoding for Semantic Recovery

    Apr 14, 2026Jingzhi Hu, Ouya Wang, Geoffrey Ye LiSemantic CommunicationWireless Communications

  3. Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models

    Apr 20, 2026Lin YaoLLM Self-CorrectionMulti-Token Prediction