AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Resource Efficient Sleep Staging via Multi-Level Masking and Prompt Learning

Lejun Ai, Yulong Li, Haodong Yi, Jixuan Xie, Yue Wang, Jia Liu, Min Chen, Rui Wang

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 1 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 multi-level masking to MASS-Base (ablation)MASS · DREAMS-SUB (40% signal)macro-F1: 15.9 -> 79.9Improved
add multi-level masking to MASS-Base (ablation)MASS · Sleep-EDF-20 (40% signal)macro-F1: 32.7 -> 79.2Improved
add multi-level masking to MASS-Base (ablation)MASS · SHHS (40% signal)macro-F1: 43.2 -> 74.6Improved
add global prompt to MASS-Base (ablation)MASS · DREAMS-SUB (40% signal)macro-F1: 15.9 -> 18.5Improved
add global prompt to MASS-Base (ablation)MASS · Sleep-EDF-78 (40% signal)macro-F1: 33.8 -> 33.9No clear effect
add global prompt to MASS-Mask (ablation)MASS · Sleep-EDF-20 (40% signal)macro-F1: 79.2 -> 79.2No clear effect
add global prompt to MASS-Mask (ablation)MASS · DREAMS-SUB (40% signal)macro-F1: 79.9 -> 80.0No clear effect
add global prompt to MASS-Mask (ablation)MASS · Sleep-EDF-78 (40% signal)macro-F1: 73.2 -> 74.4Improved
add global prompt to MASS-Mask (ablation)MASS · SHHS (40% signal)macro-F1: 74.6 -> 75.2Improved
train and test MASS with multi-level masking vs standard models at 10% signalSleep staging baselines · DREAMS-SUB (10% signal)macro-F1: 11.08 -> 75.58Improved
MASS vs NeuroNet with full signalNeuroNet · SHHS (100% signal)macro-F1: 76.87 -> 76.87No clear effect
MASS vs NeuroNet with full signalNeuroNet · Sleep-EDF-78 (100% signal)macro-F1: 75.73 -> 75.02Mixed

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