# GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring

arXiv: https://arxiv.org/abs/2605.30865 · HTML: https://mlsanity.com/paper/2605.30865/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 29 May 2026.

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

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [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)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2310.08278/) (2023)
- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [Interpolation-Prediction Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/1909.07782/) (2019)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [SimPer: Simple Self-Supervised Learning of Periodic Targets](https://mlsanity.com/paper/2210.03115/) (2022)
- [Deep Representation Learning of Electronic Health Records to Unlock Patient Stratification at Scale](https://mlsanity.com/paper/2003.06516/) (2020)
- [SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition](https://mlsanity.com/paper/2410.10624/) (2024)
- [Self-supervised transfer learning of physiological representations from free-living wearable data](https://mlsanity.com/paper/2011.12121/) (2020)
- [LSM-2: Learning from Incomplete Wearable Sensor Data](https://mlsanity.com/paper/2506.05321/) (2025)
- [HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series](https://mlsanity.com/paper/2510.25785/) (2025)
- [ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents](https://mlsanity.com/paper/2508.04038/) (2025)
- [SleepLM: Natural-Language Intelligence for Human Sleep](https://mlsanity.com/paper/2602.23605/) (2026)
- [OSF: On Pre-training and Scaling of Sleep Foundation Models](https://mlsanity.com/paper/2603.00190/) (2026)
- [MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies](https://mlsanity.com/paper/2602.17868/) (2026)
- [HEARTS: Benchmarking LLM Reasoning on Health Time Series](https://mlsanity.com/paper/2603.06638/) (2026)

## Built on by (most cited first, 7 of 7)

- [RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills](https://mlsanity.com/paper/2606.18203/) (2026)
- [TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding](https://mlsanity.com/paper/2608.00200/) (2026)
- [MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms](https://mlsanity.com/paper/2607.09749/) (2026)
- [TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series](https://mlsanity.com/paper/2609.26389/) (2026)
- [Transferable Evidence Reconstruction for Longitudinal Glucose Representations](https://mlsanity.com/paper/2609.28199/) (2026)
- [Sensor-Language-Action Models](https://mlsanity.com/paper/2610.08244/) (2026)
- [GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer](https://mlsanity.com/paper/2610.12528/) (2026)

## Abstract (arXiv)

Continuous glucose monitoring (CGM) provides a dense view of daily metabolic physiology, yet existing generic time-series and CGM-specific foundation models often encode glucose traces as entangled single-stream sequences, leaving their multiscale temporal structure only implicitly modeled. We present GlucoFM, a lightweight CGM foundation model that aligns irregular recordings to a 24-hour chronological grid, preserves observation masks, and decomposes glucose dynamics into slow-varying glycemic trend and short-term deviation streams. GlucoFM is pretrained on 109,066 hours of unlabeled CGM recordings from 477 subjects with masked contextual latent prediction over fused daily representations and temporal dynamics prediction over the two streams. Frozen pre-fusion probes confirm distinct temporal emphasis: state tokens preferentially preserve hourly glucose level, whereas event tokens better retain short-term change. Across four diverse cohorts and seven phenotype-classification tasks, GlucoFM achieves the strongest subject-disjoint linear-probing performance among evaluated baselines, improving average PR-AUC by 4.1 points over the best CGM-specific foundation model, while also supporting strong cross-dataset transfer and few-shot adaptation. Its gains are most pronounced on core metabolic outcomes, leading PR-AUC on all diabetes-risk and β-cell dysfunction tasks and on 3 of 4 insulin-resistance tasks. Beyond phenotyping, when combined with recent CGM, meal nutrition, and subject context, the same frozen encoder achieves the lowest two-hour postprandial glycemic response errors among evaluated methods for trajectory, incremental area under the curve, peak rise, and peak timing. Together, these results demonstrate that GlucoFM learns reusable frozen CGM representations spanning metabolic phenotyping and context-conditioned glucose-response prediction.