Research map / Label-efficient and robust learning / Self-supervised and contrastive
OSF: On Pre-training and Scaling of Sleep Foundation Models
Zitao Shuai, Zongzhe Xu, David Yang, Wei Wang, Yuzhe Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add channel masking to time masking (ablation) | SimCLR · MROS sleep staging | AUC: 81.4 -> 96.7 | Improved |
| add channel masking to time masking (ablation) | SimCLR · MROS hypopnea | AUC: 58.4 -> 75.6 | Improved |
| add channel masking to time masking (ablation) | DINO · MROS sleep staging | AUC: 93.6 -> 97.3 | Improved |
| add channel masking to time masking (ablation) | DINO · MROS hypopnea | AUC: 72.7 -> 77.7 | Improved |
| add time masking to channel-only masking (ablation) | SimCLR · MROS sleep staging | AUC: 94.8 -> 96.7 | Improved |
| use channel masking ratio 0.5 instead of 0.1 (ablation) | OSF · MROS sleep staging | AUC: 95.9 -> 97.3 | Improved |
| use channel masking ratio 0.5 instead of 0.9 (ablation) | OSF · MROS hypopnea | AUC: 75.0 -> 77.7 | Improved |
| add top-k selection instead of average pooling (ablation) | OSF embeddings · MROS diabetes | AUC: 60.0 -> 62.8 | Improved |
| add top-k selection instead of average pooling (ablation) | OSF embeddings · MROS hypertension | AUC: 64.2 -> 64.1 | Mixed |
| add cropping on top of channel and time masking (ablation) | OSF · MROS sleep staging | AUC: 97.3 -> 96.6 | No clear effect |
| use channel masking instead of crop-only (ablation) | OSF · MROS arousal | AUC: 85.7 -> 90.5 | Improved |
| scale encoder from 1M to 85M parameters (ablation) | OSF · MROS hypopnea | AUC | Improved |
Closest papers by meaning
- SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals (ICML 2024 · similarity 0.91)
- Generalizable Sleep Staging via Multi-Level Domain Alignment (AAAI 2024 · similarity 0.86)
- Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging (NeurIPS 2026 · similarity 0.86)
- Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.85)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.85)
- What do EEG Foundation Models Capture from Human Brain Signals? (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
