# Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach

arXiv: https://arxiv.org/abs/2507.01728 · HTML: https://mlsanity.com/paper/2507.01728/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)
- [Task-Oriented Multi-User Semantic Communications](https://mlsanity.com/paper/2112.10255/) (2021)
- [Nonlinear Information Bottleneck](https://mlsanity.com/paper/1705.02436/) (2017)
- [The Information Bottleneck Problem and Its Applications in Machine Learning](https://mlsanity.com/paper/2004.14941/) (2020)
- [Multimodal Latent Language Modeling with Next-Token Diffusion](https://mlsanity.com/paper/2412.08635/) (2024)
- [SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2308.09361/) (2023)
- [Large AI Model Empowered Multimodal Semantic Communications](https://mlsanity.com/paper/2309.01249/) (2023)
- [Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications](https://mlsanity.com/paper/2502.12096/) (2025)
- [Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis](https://mlsanity.com/paper/2205.04603/) (2022)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [Token-Domain Multiple Access: Exploiting Semantic Orthogonality for Collision Mitigation](https://mlsanity.com/paper/2502.06118/) (2025)
- [Generative Semantic Communications with Foundation Models: Perception-Error Analysis and Semantic-Aware Power Allocation](https://mlsanity.com/paper/2411.04575/) (2024)
- [ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access](https://mlsanity.com/paper/2505.10946/) (2025)
- [Multi-Task Semantic Communications via Large Models](https://mlsanity.com/paper/2503.22064/) (2025)

## Built on by (most cited first, 11 of 11)

- [Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding](https://mlsanity.com/paper/2603.02470/) (2026)
- [TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems](https://mlsanity.com/paper/2605.21553/) (2026)
- [Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation](https://mlsanity.com/paper/2608.28086/) (2026)
- [Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey](https://mlsanity.com/paper/2604.07857/) (2026)
- [TWIST: Closed-Loop token Synchronization for Application-Aware Wireless Digital Twins](https://mlsanity.com/paper/2605.27205/) (2026)
- [Explainable Task-Oriented Token Communication for AI-Native 6G Networks](https://mlsanity.com/paper/2606.14808/) (2026)
- [TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Driving](https://mlsanity.com/paper/2608.01998/) (2026)
- [Token-Oriented Semantic Communication with Pretrained Vision Transformers](https://mlsanity.com/paper/2608.25410/) (2026)
- [From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity](https://mlsanity.com/paper/2609.10714/) (2026)
- [Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities](https://mlsanity.com/paper/2610.01826/) (2026)
- [Queue-Aware Token Communications: Bridging AI Representation and Wireless Service](https://mlsanity.com/paper/2610.16730/) (2026)

## Abstract (arXiv)

This letter proposes UniToCom, a unified token communication paradigm that treats tokens as the fundamental units for both processing and wireless transmission. Specifically, to enable efficient token representations, we propose a generative information bottleneck (GenIB) principle, which facilitates the learning of tokens that preserve essential information while supporting reliable generation across multiple modalities. By doing this, GenIB-based tokenization is conducive to improving the communication efficiency and reducing computational complexity. Additionally, we develop σ-GenIB to address the challenges of variance collapse in autoregressive modeling, maintaining representational diversity and stability. Moreover, we employ a causal Transformer-based multimodal large language model (MLLM) at the receiver to unify the processing of both discrete and continuous tokens under the next-token prediction paradigm. Simulation results validate the effectiveness and superiority of the proposed UniToCom compared to baselines under dynamic channel conditions. By integrating token processing with MLLMs, UniToCom enables scalable and generalizable communication in favor of multimodal understanding and generation, providing a potential solution for next-generation intelligent communications.