# Lightweight Adaptive Feature Composition for Heterogeneous Downstream Adaptation of Wireless Foundation Models

arXiv: https://arxiv.org/abs/2606.10277 · HTML: https://mlsanity.com/paper/2606.10277/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice](https://mlsanity.com/paper/2203.05962/) (2022)
- [ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions](https://mlsanity.com/paper/2403.07392/) (2024)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Large Language Models Empowered Autonomous Edge AI for Connected Intelligence](https://mlsanity.com/paper/2307.02779/) (2023)
- [MIMO Channel Estimation using Score-Based Generative Models](https://mlsanity.com/paper/2204.07122/) (2022)
- [LLM4CP: Adapting Large Language Models for Channel Prediction](https://mlsanity.com/paper/2406.14440/) (2024)
- [WirelessGPT: A Generative Pre-trained Multi-task Learning Framework for Wireless Communication](https://mlsanity.com/paper/2502.06877/) (2025)
- [Big AI Models for 6G Wireless Networks: Opportunities, Challenges, and Research Directions](https://mlsanity.com/paper/2308.06250/) (2023)
- [Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals](https://mlsanity.com/paper/2312.00751/) (2023)
- [WiFo: Wireless Foundation Model for Channel Prediction](https://mlsanity.com/paper/2412.08908/) (2024)
- [Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning](https://mlsanity.com/paper/2012.14768/) (2020)
- [Exploiting Deep Representations for Neural Machine Translation](https://mlsanity.com/paper/1810.10181/) (2018)
- [A Multi-Task Foundation Model for Wireless Channel Representation Using Contrastive and Masked Autoencoder Learning](https://mlsanity.com/paper/2505.09160/) (2025)
- [LLM4WM: Adapting LLM for Wireless Multi-Tasking](https://mlsanity.com/paper/2501.12983/) (2025)
- [Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Training](https://mlsanity.com/paper/2302.04368/) (2023)
- [A Wireless Foundation Model for Multi-Task Prediction](https://mlsanity.com/paper/2507.05938/) (2025)
- [CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing](https://mlsanity.com/paper/2412.06861/) (2024)
- [Large Language Models for Wireless Communications: From Adaptation to Autonomy](https://mlsanity.com/paper/2507.21524/) (2025)
- [Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification](https://mlsanity.com/paper/2209.15168/) (2022)
- [Resource-Efficient Beam Prediction in mmWave Communications with Multimodal Realistic Simulation Framework](https://mlsanity.com/paper/2504.05187/) (2025)
- [WiFo-MiSAC: A Wireless Foundation Model for Multimodal Sensing and Communication Integration via Synesthesia of Machines (SoM)](https://mlsanity.com/paper/2604.18255/) (2026)
- [Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration](https://mlsanity.com/paper/2506.07647/) (2025)
- [Model-Driven Deep Learning-Based MIMO-OFDM Detector: Design, Simulation, and Experimental Results](https://mlsanity.com/paper/2206.10909/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks](https://mlsanity.com/paper/2608.14694/) (2026)

## Abstract (arXiv)

Mobile systems increasingly rely on heterogeneous learning-enabled wireless functions, for which separate taskspecific models incur redundant training and model-management overhead. Wireless foundation models (WFMs) enable these functions to share a pretrained backbone, but existing adaptation either updates the backbone per task or relies on an inflexible final-layer representation. We observe that intermediate WFM layers exhibit distinct depth-dependent correlation structures. Based on this observation, we propose a Routing Adapter for Feature Composition (RAFC), which summarizes selected hidden states into compact descriptors, generates task- and sampledependent routing weights, and combines the original fullresolution features without updating the pretrained backbone. Its gains arise from giving each task adaptive access to complementary representations across multiple depths rather than restricting it to the final layer. Experiments across four task categories and three WFM backbones show improvements in every evaluated backbone-task pair, with mean relative gains across the four task categories ranging from 2.9% to 35.9%, while RAFC adds only 0.003M-0.049M trainable parameters across the evaluated backbones. Experiments on a portable softwaredefined radio testbed further demonstrate improved end-to-end receiver robustness, particularly under partial-band co-channel interference. These results establish RAFC as a lightweight, model-agnostic, and interpretable adaptation interface for WFMs in mobile systems.