Research map / Vision-language and multimodal / Human and embodied modeling
SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
Keondo Park, Younghoon Na, You Rim Choi, Hyunwoo Ryu, Hyun-Woo Shin, Hyung-Sin Kim
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 Macro-Encoder (DGCL) to Micro-Encoder (ablation) | SleepMaMi · Sleep stage classification | accuracy: 79.8 -> 81.9 | Improved |
| Add Macro-Encoder (DGCL) to Micro-Encoder (ablation) | SleepMaMi · Sex classification | accuracy: 80.1 -> 88.2 | Improved |
| Add Macro-Encoder (DGCL) to Micro-Encoder (ablation) | SleepMaMi · Age regression | MAE: 9.45 -> 6.73 | Improved |
| Add Macro-Encoder (DGCL) to Micro-Encoder (ablation) | SleepMaMi · AHI regression | MAE: 9.69 -> 8.40 | Improved |
| Add Macro-Encoder (DGCL) to Micro-Encoder (ablation) | SleepMaMi · Disease prediction SHHS1 | C-index: 0.729 -> 0.753 | Improved |
| Use SleepMaMi instead of SleepFM-Disease | sleep staging · SHHS1 sleep staging | accuracy: 69.7 -> 81.9 | Improved |
| Use SleepMaMi instead of SleepFM-Disease | sleep staging held-out · SOF sleep staging | accuracy: 60.1 -> 79.1 | Improved |
| Use SleepMaMi instead of MOMENT-Base | sleep staging · CFS sleep staging | accuracy: 71.4 -> 80.7 | Improved |
| Use SleepMaMi instead of SleepFM-Disease | SDB segmentation · CFS SDB | F1: 46.6 -> 52.3 | Improved |
| Use SleepMaMi instead of UniTS | SDB segmentation · SOF SDB | F1: 35.7 -> 32.7 | Hurt |
| Use SleepMaMi instead of UniTS | SDB segmentation · SHHS1 SDB | F1: 48.8 -> 48.5 | No clear effect |
| Use SleepMaMi instead of SleepFM-Disease | disease prediction · SHHS1 Angina | C-index: 0.632 -> 0.778 | Improved |
Closest papers by meaning
- SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals (ICML 2024 · similarity 0.91)
- OSF: On Pre-training and Scaling of Sleep Foundation Models (ICML 2026 · similarity 0.91)
- Generalizable Sleep Staging via Multi-Level Domain Alignment (AAAI 2024 · similarity 0.86)
- Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.86)
- Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination (NeurIPS 2024 · similarity 0.85)
- Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging (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.
