# CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models

arXiv: https://arxiv.org/abs/2607.14975 · HTML: https://mlsanity.com/paper/2607.14975/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [LLM4CP: Adapting Large Language Models for Channel Prediction](https://mlsanity.com/paper/2406.14440/) (2024)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [WiFo: Wireless Foundation Model for Channel Prediction](https://mlsanity.com/paper/2412.08908/) (2024)
- [A Survey of Beam Management for mmWave and THz Communications Towards 6G](https://mlsanity.com/paper/2308.02135/) (2023)
- [A Distributed Massive MIMO Channel Sounder for "Big CSI Data"-driven Machine Learning](https://mlsanity.com/paper/2206.15302/) (2022)
- [A Wireless Foundation Model for Multi-Task Prediction](https://mlsanity.com/paper/2507.05938/) (2025)
- [CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network](https://mlsanity.com/paper/2205.05775/) (2022)
- [Towards channel foundation models (CFMs): Motivations, methodologies and opportunities](https://mlsanity.com/paper/2507.13637/) (2025)
- [Multimodal-Wireless: A Large-Scale Dataset for Sensing and Communication](https://mlsanity.com/paper/2511.03220/) (2025)
- [CSI-MAE: A Masked Autoencoder-based Channel Foundation Model](https://mlsanity.com/paper/2601.03789/) (2026)
- [DyLoc: Dynamic Localization for Massive MIMO Using Predictive Recurrent Neural Networks](https://mlsanity.com/paper/2101.07848/) (2021)
- [AI for CSI Feedback Enhancement in 5G-Advanced](https://mlsanity.com/paper/2206.15132/) (2022)
- [Enabling 6G Through Multi-Domain Channel Extrapolation: Opportunities and Challenges of Generative Artificial Intelligence](https://mlsanity.com/paper/2509.01125/) (2025)
- [AI-Driven Channel State Information (CSI) Extrapolation for 6G: Current Situations, Challenges and Future Research](https://mlsanity.com/paper/2601.00159/) (2026)
- [Filter-and-Attend: Wireless Channel Foundation Model with Noise-Plus-Interference Suppression Structure](https://mlsanity.com/paper/2509.15993/) (2025)
- [SSNet: Flexible and robust channel extrapolation for fluid antenna systems enabled by an self-supervised learning framework](https://mlsanity.com/paper/2509.17797/) (2025)
- [WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks](https://mlsanity.com/paper/2601.09186/) (2026)
- [Enhanced Fingerprint-based Positioning With Practical Imperfections: Deep learning-based approaches](https://mlsanity.com/paper/2509.01197/) (2025)
- [CSI-CLIP++: A Scalable Channel Foundation Model for Wireless Communication via CIR-CSI Consistency](https://mlsanity.com/paper/2606.25714/) (2026)
- [CSI Measurements and Initial Results for Massive MIMO to UAV Communication](https://mlsanity.com/paper/2312.15188/) (2023)
- [Sidelink Positioning: Standardization Advancements, Challenges and Opportunities](https://mlsanity.com/paper/2512.24803/) (2025)
- [Generalizable and Robust Beam Prediction for 6G Networks: An Deep-Learning Framework with Positioning Feature Fusion](https://mlsanity.com/paper/2602.09685/) (2026)
- [AI/ML for mobile networks: Current status in Rel. 19 and challenges ahead](https://mlsanity.com/paper/2603.14317/) (2026)

## Abstract (arXiv)

Channel foundation models (CFMs) are commonly evaluated in model-specific pipelines that differ in data, radio configurations, partitions, adaptation procedures, task definitions, and metrics, preventing reproducible comparison across CFMs and against task-specific networks. We release CFM-Bench, a unified multi-domain, multi-task benchmark comprising 157,900 official single-frame examples from six domains spanning 3GPP statistical simulation, two ray-tracing pipelines, terrestrial and aerial measurements, and synchronized vehicular multimodal simulation. Source-specific interfaces preserve complex channel state information (CSI) and the physical metadata available in each domain while allowing documented model-specific preprocessing. To reduce spatio-temporal leakage, official partitions isolate complete trajectories, measurement sessions, flights, vehicle links, simulation realizations, or buffered spatial regions. CFM-Bench excludes all benchmark splits from foundation-model pretraining, reserves the official training split for downstream fine-tuning, and reports the data used during model development. Six task groups across PHY, RAN, and ISAC applications cover CSI feedback, frequency and temporal channel extrapolation, propagation-state classification, current- and future-beam prediction, and single-frame and temporal localization. Representative experiments on CSI feedback, channel extrapolation, current-beam prediction, and wireless positioning provide reproducible reference results for pretrained channel-prediction models and task-specific neural networks. These results show that relative model performance can vary across data domains, highlighting the importance of using common data partitions, task definitions, and evaluation metrics. CFM-Bench provides a common substrate for evaluating the transferability of channel representations across models, domains, and tasks.