# Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication

arXiv: https://arxiv.org/abs/2509.09168 · HTML: https://mlsanity.com/paper/2509.09168/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2006.05078/) (2020)
- [A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems](https://mlsanity.com/paper/1902.10265/) (2019)
- [On The Computational Complexity of Self-Attention](https://mlsanity.com/paper/2209.04881/) (2022)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Less Data, More Knowledge: Building Next Generation Semantic Communication Networks](https://mlsanity.com/paper/2211.14343/) (2022)
- [Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention](https://mlsanity.com/paper/2209.13802/) (2022)
- [Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications](https://mlsanity.com/paper/2502.12096/) (2025)
- [Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2106.11890/) (2021)
- [Adaptive Semantic Token Selection for AI-native Goal-oriented Communications](https://mlsanity.com/paper/2405.02330/) (2024)
- [Contrastive Learning and Adversarial Disentanglement for Privacy-Aware Task-Oriented Semantic Communication](https://mlsanity.com/paper/2410.22784/) (2024)
- [Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2304.01914/) (2023)

## Built on by (most cited first, 2 of 2)

- [Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge](https://mlsanity.com/paper/2509.09955/) (2025)
- [From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity](https://mlsanity.com/paper/2609.10714/) (2026)

## Abstract (arXiv)

Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across noisy wireless channels. However, their substantial computational demands remain a major barrier to practical deployment in resource-constrained 6G networks. In this paper, we present a training-free framework for adaptive token merging in pretrained vision transformers to jointly reduce inference time and transmission resource usage. We formulate the selection of per-layer merging proportions as a multi-objective optimization problem to balance accuracy and computational cost. We employ Gaussian process-based Bayesian optimization to construct a Pareto frontier of optimal configurations, enabling flexible runtime adaptation to dynamic application requirements and channel conditions. Extensive experiments demonstrate that our method consistently outperforms other baselines and achieves significant reductions in floating-point operations while maintaining competitive accuracy across a wide range of signal-to-noise ratio (SNR) conditions. Additional results highlight the effectiveness of adaptive policies that adjust merging aggressiveness in response to channel quality, providing a practical mechanism to trade off latency and semantic fidelity on demand. These findings establish a scalable and efficient approach for deploying transformer-based semantic communication in future edge intelligence systems.