# Multimodal-Wireless: A Large-Scale Dataset for Sensing and Communication

arXiv: https://arxiv.org/abs/2511.03220 · HTML: https://mlsanity.com/paper/2511.03220/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2025.

## Built on by (most cited first, 6 of 6)

- [Large Model Enabled Embodied Intelligence for 6G Integrated Perception, Communication, and Computation Network](https://mlsanity.com/paper/2512.15109/) (2025)
- [Improving Channel Estimation via Multimodal Diffusion Models with Flow Matching](https://mlsanity.com/paper/2603.13440/) (2026)
- [Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction](https://mlsanity.com/paper/2603.16143/) (2026)
- [CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models](https://mlsanity.com/paper/2607.14975/) (2026)
- [Vision-Wireless Fusion for Multi-User Localization: A Cross-Modal Transformer Approach](https://mlsanity.com/paper/2609.23372/) (2026)
- [AIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISAC](https://mlsanity.com/paper/2609.39964/) (2026)

## Abstract (arXiv)

This paper presents Multimodal-Wireless, a large-scale open-source dataset for multimodal sensing and communication research. The dataset is generated through an integrated and customizable data pipeline built upon the CARLA simulator and Sionna framework, and features high-resolution communication channel state information (CSI) fully synchronized with five other sensor modalities, namely LiDAR, RGB and depth camera, inertial measurement unit (IMU) and radar, all sampled at 100 Hz. It contains approximately 160,000 frames collected across four virtual towns, sixteen communication scenarios, and three weather conditions. This paper provides a comprehensive overview of the dataset, outlining its key features, overall framework, and technical implementation details. In addition, it explores potential research applications concerning communication and collaborative perception, exemplified by beam prediction using a multimodal large language model. The dataset is open in https://le-liang.github.io/mmw/.