{"ID":5860537,"CreatedAt":"2026-07-05T00:12:12.706648185Z","UpdatedAt":"2026-07-09T12:17:35.905372468Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2604.04297","arxiv_id":"2604.04297","title":"PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence","abstract":"Physiological foundation models (FMs) have shown promise for biosignal representation learning, yet most remain confined to a single modality such as EEG, ECG, or PPG, largely because paired multimodal datasets are scarce. In this paper, we present PanLUNA, a compact 5.4M-parameter pan-modal FM that jointly processes EEG, ECG, and PPG within a single shared encoder. Extending LUNA's channel-unification module, PanLUNA treats multimodal channels as entries in a unified query set augmented with sensor-type embeddings, enabling efficient cross-modal early fusion while remaining inherently robust to missing modalities at inference time. Despite its small footprint, PanLUNA matches or exceeds models up to 57$\\times$ larger: 81.21% balanced accuracy on TUAB abnormal EEG detection and state-of-the-art 0.7416 balanced accuracy on HMC multimodal sleep staging. Quantization-aware training with INT8 weights recovers $\\geq$96% of full-precision performance, and deployment on the GAP9 ultra-low-power RISC-V microcontroller for wearables achieves 325.6 ms latency and 18.8 mJ per 10-second, 12-lead ECG inference, and 1.206 s latency at 68.65 mJ for multimodal 5-channel sleep staging over 30-second epochs.","url_abs":"https://arxiv.org/abs/2604.04297v1","url_pdf":"https://arxiv.org/pdf/2604.04297v1","authors":"Marija Zelic, Anna Tegon, Yawei Li, Thorir Mar Ingolfsson, Luca Benini","published":"2026-04-05T22:35:42Z","has_code":false}