{"ID":2879618,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06966","arxiv_id":"2509.06966","title":"Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings","abstract":"High-quality, medically validated labels exist for clinical actigraphy data but not for ubiquitous consumer wearables like the Apple Watch. Manually labeling wearables data is expensive and doesn't scale. This paper offers a novel framework that transfers valuable labels from a source domain (e.g., actigraphy) to a target domain (e.g., Apple Watch) without requiring paired data. Instead of working with raw time-series signals, we project both domains into a shared latent embedding space using time-series foundation models (TSFMs) and develop a new framework to align the cross-device representations. Our method, Adversarial Alignment of TSFM Embeddings forces the distributions of source and target embeddings to align within this space, facilitating label transfer across device type.","short_abstract":"High-quality, medically validated labels exist for clinical actigraphy data but not for ubiquitous consumer wearables like the Apple Watch. Manually labeling wearables data is expensive and doesn't scale. This paper offers a novel framework that transfers valuable labels from a source domain (e.g., actigraphy) to a tar...","url_abs":"https://arxiv.org/abs/2509.06966","url_pdf":"https://arxiv.org/pdf/2509.06966v1","authors":"[\"Neal G. Ravindra\",\"Arijit Sehanobish\"]","published":"2025-08-22T23:22:41Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}