# LSM-2: Learning from Incomplete Wearable Sensor Data

arXiv: https://arxiv.org/abs/2506.05321 · HTML: https://mlsanity.com/paper/2506.05321/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 76 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://mlsanity.com/paper/2302.00861/) (2023)
- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram](https://mlsanity.com/paper/2402.09450/) (2024)
- [Exploring Contrastive Learning in Human Activity Recognition for Healthcare](https://mlsanity.com/paper/2011.11542/) (2020)
- [Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data](https://mlsanity.com/paper/2206.02909/) (2022)
- [PaPaGei: Open Foundation Models for Optical Physiological Signals](https://mlsanity.com/paper/2410.20542/) (2024)
- [Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://mlsanity.com/paper/2301.08871/) (2023)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [MAEEG: Masked Auto-encoder for EEG Representation Learning](https://mlsanity.com/paper/2211.02625/) (2022)
- [ReMasker: Imputing Tabular Data with Masked Autoencoding](https://mlsanity.com/paper/2309.13793/) (2023)
- [Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings](https://mlsanity.com/paper/2502.01108/) (2025)
- [Data augmentation for learning predictive models on EEG: a systematic comparison](https://mlsanity.com/paper/2206.14483/) (2022)
- [Self-supervised transfer learning of physiological representations from free-living wearable data](https://mlsanity.com/paper/2011.12121/) (2020)
- [REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning](https://mlsanity.com/paper/2311.00519/) (2023)

## Built on by (most cited first, 23 of 23)

- [HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series](https://mlsanity.com/paper/2510.25785/) (2025)
- [OSF: On Pre-training and Scaling of Sleep Foundation Models](https://mlsanity.com/paper/2603.00190/) (2026)
- [CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models](https://mlsanity.com/paper/2512.02180/) (2025)
- [GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring](https://mlsanity.com/paper/2605.30865/) (2026)
- [Towards a General Intelligence and Interface for Wearable Health Data](https://mlsanity.com/paper/2605.22759/) (2026)
- [Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models](https://mlsanity.com/paper/2601.12215/) (2026)
- [Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning](https://mlsanity.com/paper/2605.00973/) (2026)
- [Learning Transferable Sensor Models via Language-Informed Pretraining](https://mlsanity.com/paper/2603.11950/) (2026)
- [Wearable Foundation Models Should Go Beyond Static Encoders](https://mlsanity.com/paper/2603.19564/) (2026)
- [Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data](https://mlsanity.com/paper/2603.10961/) (2026)
- [WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning](https://mlsanity.com/paper/2606.18147/) (2026)
- [OpenMHC: Accelerating the Science of Wearable Foundation Models](https://mlsanity.com/paper/2607.16235/) (2026)
- [Learning Longitudinal Health Representations from EHR and Wearable Data](https://mlsanity.com/paper/2601.12227/) (2026)
- [A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models](https://mlsanity.com/paper/2605.28563/) (2026)
- [Next-Token Prediction Learns Generalisable Representations of Sleep Physiology](https://mlsanity.com/paper/2606.09605/) (2026)
- [TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding](https://mlsanity.com/paper/2608.00200/) (2026)
- [Prototype-based Self-Supervised Multimodal Learning for PPG and Accelerometry Signals](https://mlsanity.com/paper/2510.09764/) (2025)
- [Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models](https://mlsanity.com/paper/2511.18829/) (2025)
- [Learning Representations from Incomplete EHR Data with Dual-Masked Autoencoding](https://mlsanity.com/paper/2602.15159/) (2026)
- [WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms](https://mlsanity.com/paper/2605.09173/) (2026)
- [VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals](https://mlsanity.com/paper/2605.18837/) (2026)
- [Foundation models for movement data: Are they ready for prime-time?](https://mlsanity.com/paper/2608.13316/) (2026)
- [Variable Input Masked Autoencoders for Wrist-Worn Accelerometry](https://mlsanity.com/paper/2610.17383/) (2026)

## Abstract (arXiv)

Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial challenge for self-supervised learning (SSL) models that typically assume complete data inputs. This paper introduces the second generation of Large Sensor Model (LSM-2) with Adaptive and Inherited Masking (AIM), a novel SSL approach that learns robust representations directly from incomplete data without requiring explicit imputation. AIM's core novelty lies in its use of learnable mask tokens to model both existing ("inherited") and artificially introduced missingness, enabling it to robustly handle fragmented real-world data during inference. Pre-trained on an extensive dataset of 40M hours of day-long multimodal sensor data, our LSM-2 with AIM achieves the best performance across a diverse range of tasks, including classification, regression and generative modeling. Furthermore, LSM-2 with AIM exhibits superior scaling performance, and critically, maintains high performance even under targeted missingness scenarios, reflecting clinically coherent patterns, such as the diagnostic value of nighttime biosignals for hypertension prediction. This makes AIM a more reliable choice for real-world wearable data applications.