Wearable Foundation Models Should Go Beyond Static Encoders

TL;DR

This paper argues that wearable foundation models should evolve from static encoders to longitudinal, anticipatory systems capable of reasoning over personal health trajectories for better chronic condition management.

Contribution

It identifies three foundational shifts—rich data, longitudinal modeling, and agentic inference—necessary to advance WFMs beyond static, retrospective health monitoring.

Findings

Highlights limitations of current static WFMs for chronic health conditions

Proposes a framework for integrating multimodal, long-term personal data

Emphasizes the importance of decision-making and intervention capabilities

Abstract

Wearable foundation models (WFMs), trained on large volumes of data collected by affordable, always-on devices, have demonstrated strong performance on short-term, well-defined health monitoring tasks, including activity recognition, fitness tracking, and cardiovascular signal assessment. However, most existing WFMs primarily map short temporal windows to predefined labels via static encoders, emphasizing retrospective prediction rather than reasoning over evolving personal history, context, and future risk trajectories. As a result, they are poorly suited for modeling chronic, progressive, or episodic health conditions that unfold over weeks, months or years. Hence, we argue that WFMs must move beyond static encoders and be explicitly designed for longitudinal, anticipatory health reasoning. We identify three foundational shifts required to enable this transition: (1) Structurally rich data, which goes beyond isolated datasets or outcome-conditioned collection to integrated multimodal, long-term personal trajectories, and contextual metadata, ideally supported by open and interoperable data ecosystems; (2) Longitudinal-aware multimodal modeling, which prioritizes long-context inference, temporal abstraction, and personalization over cross-sectional or population-level prediction; and (3) Agentic inference systems, which move beyond static prediction to support planning, decision-making, and clinically grounded intervention under uncertainty. Together, these shifts reframe wearable health monitoring from retrospective signal interpretation toward continuous, anticipatory, and human-aligned health support.