{
  "annotation_id": "f6ddce48-9dd9-46e3-b94b-2c9a32698320",
  "date_created": "2026-02-17T05:53:20.072000Z",
  "date_modified": "2026-02-17T05:53:20.072000Z",
  "file_hash": "205b08c4c1e7ec0f29623bf7503a2bda9199a94a2e8224b05103e9af7f12c982",
  "private": false,
  "record": {
    "abstract": "The growing adoption of sensor-rich intelligent systems has boosted the use of multi-modal sensing to improve wireless communications. However, traditional methods require extensive manual design of data preprocessing, network architecture, and task-specific fine-tuning, which limits both development scalability and real-world deployment. To address this, we propose WiFo-M$^2$, a foundation model that can be easily plugged into existing deep learning-based transceivers for universal performance gains. To extract generalizable out-of-band (OOB) channel features from multi-modal sensing, we introduce ContraSoM, a contrastive pre-training strategy. Once pre-trained, WiFo-M$^2$ infers future OOB channel features from historical sensor data and strengthens feature robustness via modality-specific data augmentation. Experiments show that WiFo-M$^2$ improves performance across multiple transceiver designs and demonstrates strong generalization to unseen scenarios.",
    "arxiv_id": "2601.09179",
    "authors": [
      "Haotian Zhang",
      "Shijian Gao",
      "Xiang Cheng"
    ],
    "categories": [
      "eess.SP"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "WiFo-M$^2$: Plug-and-Play Multi-Modal Sensing via Foundation Model to Empower Wireless Communications",
    "url": "https://arxiv.org/abs/2601.09179",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "8cd32949-b515-4975-926f-c1dbf7aee87d",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}