Explainable Task-Oriented Token Communication for AI-Native 6G Networks

2026-06-12

AI Summary

This work addresses three key challenges in task-oriented image communication: insufficient task representation, weak coordination between visual and task tokens, and poor decision interpretability. To overcome these limitations, the authors propose ET-TokenCom, a novel framework that explicitly introduces task tokens to guide the selection and weighted transmission of visual tokens, thereby establishing an end-to-end communication pipeline seamlessly integrating perception, transmission, and reasoning. The framework incorporates cross-modal attention mechanisms and attention heatmaps to enable token decoding at the receiver with highly interpretable outputs. Experimental results demonstrate that ET-TokenCom significantly enhances task performance, robustness, and decision transparency compared to existing approaches.

Abstract

The integration of Foundation Models (FMs) and wireless communications is driving the evolution of image communication from bit-accurate transmission toward task-oriented transmission. However, existing task-oriented image communication methods still face three major challenges: insufficient task-oriented Token representation, inadequate collaboration between Visual Tokens and Task Tokens, and limited interpretability of task decisions. To address these challenges, we propose an Explainable Task-Oriented Token Communication (ET-TokenCom) framework. By treating Tokens as unified units for information representation and transmission, the proposed framework constructs an end-to-end communication link that spans visual perception, wireless transmission, and task reasoning. At the transmitter, the ET-TokenCom framework extracts Visual Tokens from images to preserve low-level visual information. Meanwhile, Task Tokens generated by the FM are introduced to represent the target information and decision intent required by the current task. A Cross-Modal Attention (CMA) fusion mechanism is further designed, enabling Task Tokens to explicitly guide the selection, weighting, and transmission of Visual Tokens. At the receiver, the framework integrates Token decoding with an explainable output mechanism, where attention heatmaps are generated to highlight critical perceptual regions under different task objectives and reveal the influence of Task Tokens on the outputs. Finally, simulation results validate the effectiveness and robustness of the proposed ET-TokenCom framework.

Problem

• Task-Oriented Communication
• Token Representation
• Cross-Modal Collaboration
• Explainable AI
• Foundation Models

Innovation

• Task-Oriented Communication
• Foundation Models
• Token Representation
• Cross-Modal Attention
• Explainable AI