# Foundation models for movement data: Are they ready for prime-time?

arXiv: https://arxiv.org/abs/2608.13316 · HTML: https://mlsanity.com/paper/2608.13316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data](https://mlsanity.com/paper/2206.02909/) (2022)
- [Neuro-GPT: Towards A Foundation Model for EEG](https://mlsanity.com/paper/2311.03764/) (2023)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals](https://mlsanity.com/paper/2412.09758/) (2024)
- [UniMTS: Unified Pre-training for Motion Time Series](https://mlsanity.com/paper/2410.19818/) (2024)
- [LSM-2: Learning from Incomplete Wearable Sensor Data](https://mlsanity.com/paper/2506.05321/) (2025)
- [Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions](https://mlsanity.com/paper/2507.00191/) (2025)
- [Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers](https://mlsanity.com/paper/2412.06639/) (2024)
- [Machine-learning for photoplethysmography analysis: Benchmarking feature, image, and signal-based approaches](https://mlsanity.com/paper/2502.19949/) (2025)
- [S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models](https://mlsanity.com/paper/2310.06715/) (2023)
- [Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook](https://mlsanity.com/paper/2604.02711/) (2026)

## Abstract (arXiv)

Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking. We present the first comprehensive evaluation of four open-source accelerometer FMs against supervised baselines covering 19 tasks across the domains of activity recognition including activities of daily living, clinical monitoring, and physiological inference. We find task-dependent performance results: supervised models remain competitive with FMs on human action recognition (HAR), with no consistent advantage for either, while selected FMs lead on fall and stress detection and are the most robust to sensor-placement variation. As frozen feature extractors, FMs are strongest for demographic inference, whereas sleep staging performance remains near chance level for all models. The internal FM representations show strong similarity across layers, highlighting potential for future FM improvements. Linear and frozen probing reveals that UniMTS provides the strongest representations and is the only FM that surpasses the supervised baselines without finetuning. Concept discovery analysis shows all models capture high-intensity activities clearly but struggle with sedentary, complex or ambiguous activities. We provide scenario-based deployment recommendations. Furthermore, we identify FM-derived activity profile inference-moving beyond fixed category classification-as a promising research direction.