# SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures

DevFeed: [SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures](<https://devfeed.tech/articles/sleepmami-a-universal-sleep-foundation-model-for-integrating-macro-and-micro-structures-96815.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.07628>)

Author: Keondo Park, Younghoon Na, Yourim Choi, Hyunwoo Ryu, Hyun-Woo Shin, Hyung-Sin Kim

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [design](<https://devfeed.tech/tags/design.md>), [features](<https://devfeed.tech/tags/features.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [framework](<https://devfeed.tech/tags/framework.md>), [global](<https://devfeed.tech/tags/global.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [learning](<https://devfeed.tech/tags/learning.md>), [medicine](<https://devfeed.tech/tags/medicine.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [sleep](<https://devfeed.tech/tags/sleep.md>)

## AI overview

SleepMaMi combines full-night sleep patterns with fine-grained biosignal features using two encoders: a Macro-Encoder models overnight temporal dependencies, while a Micro-Encoder captures short-term signal characteristics. The Macro-Encoder uses demographic-guided contrastive learning to align sleep patterns with metadata such as age, sex, and BMI; the Micro-Encoder combines masked autoencoding with multimodal contrastive learning. Pretrained on more than 20,000 polysomnography recordings (158,000 hours), the model reportedly matches or outperforms existing foundation models across varied downstream tasks, with stronger generalizability and label-efficient adaptation. The supplied text does not specify the tasks or evaluation details.

## Source excerpt

arXiv:2602.07628v3 Announce Type: replace-cross Abstract: While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi , a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age, sex and BMI to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of $>$20,000 PSG recordings (158K hours),SleepMaMi outperforms or matches state-of-the-art existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.