GlucoFM decomposes CGM traces into dual state-event streams, pretrains on 109k hours of unlabeled data, and reports superior subject-disjoint performance on seven clinical tasks across four cohorts.
OSF: On Pre-training and Scaling of Sleep Foundation Models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack an in-depth understanding of the pre-training process and scaling patterns that lead to more generalizable sleep FMs. To fill this gap, we curate a massive corpus of 166,500 hours of sleep recordings from nine public sources and establish SleepBench, a comprehensive, fully open-source benchmark. Leveraging SleepBench, we systematically evaluate four families of self-supervised pre-training objectives and uncover three critical findings: (1) existing FMs fail to generalize to missing channels at inference; (2) channel-invariant feature learning is essential for pre-training; and (3) scaling sample size, model capacity, and multi-source data mixture consistently improves downstream performance.With an enhanced pre-training and scaling recipe, we introduce OSF, a family of sleep FMs that achieves state-of-the-art performance across nine datasets on diverse sleep and disease prediction tasks. Further analysis of OSF also reveals intriguing properties in sample efficiency, hierarchical aggregation, and cross-dataset scaling.
years
2026 4representative citing papers
Controlled large-scale pretraining on 18.2M hours of wearables shows self-supervised motion models beat scratch training, with triaxial fidelity, data diversity, and task-matched windows mattering more than model size alone.
Next-token prediction on multi-modal tokenized sleep signals yields embeddings that match supervised performance with far less labels and generalize to daytime heart data.
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
citing papers explorer
-
GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
GlucoFM decomposes CGM traces into dual state-event streams, pretrains on 109k hours of unlabeled data, and reports superior subject-disjoint performance on seven clinical tasks across four cohorts.
-
Inertia-1: An Open Exploration of Wearable Motion Foundation Models
Controlled large-scale pretraining on 18.2M hours of wearables shows self-supervised motion models beat scratch training, with triaxial fidelity, data diversity, and task-matched windows mattering more than model size alone.
-
Next-Token Prediction Learns Generalisable Representations of Sleep Physiology
Next-token prediction on multi-modal tokenized sleep signals yields embeddings that match supervised performance with far less labels and generalize to daytime heart data.
-
TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.