AI Paper Atlas

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

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add Macro-Encoder (DGCL) to Micro-Encoder (ablation)SleepMaMi · Sleep stage classificationaccuracy: 79.8 -> 81.9Improved
Add Macro-Encoder (DGCL) to Micro-Encoder (ablation)SleepMaMi · Sex classificationaccuracy: 80.1 -> 88.2Improved
Add Macro-Encoder (DGCL) to Micro-Encoder (ablation)SleepMaMi · Age regressionMAE: 9.45 -> 6.73Improved
Add Macro-Encoder (DGCL) to Micro-Encoder (ablation)SleepMaMi · AHI regressionMAE: 9.69 -> 8.40Improved
Add Macro-Encoder (DGCL) to Micro-Encoder (ablation)SleepMaMi · Disease prediction SHHS1C-index: 0.729 -> 0.753Improved
Use SleepMaMi instead of SleepFM-Diseasesleep staging · SHHS1 sleep stagingaccuracy: 69.7 -> 81.9Improved
Use SleepMaMi instead of SleepFM-Diseasesleep staging held-out · SOF sleep stagingaccuracy: 60.1 -> 79.1Improved
Use SleepMaMi instead of MOMENT-Basesleep staging · CFS sleep stagingaccuracy: 71.4 -> 80.7Improved
Use SleepMaMi instead of SleepFM-DiseaseSDB segmentation · CFS SDBF1: 46.6 -> 52.3Improved
Use SleepMaMi instead of UniTSSDB segmentation · SOF SDBF1: 35.7 -> 32.7Hurt
Use SleepMaMi instead of UniTSSDB segmentation · SHHS1 SDBF1: 48.8 -> 48.5No clear effect
Use SleepMaMi instead of SleepFM-Diseasedisease prediction · SHHS1 AnginaC-index: 0.632 -> 0.778Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy