Learning Transferable Sensor Models via Language-Informed Pretraining

TL;DR

SLIP is a novel framework that learns language-aligned sensor representations, enabling zero-shot transfer and flexible sensor configurations across diverse datasets, improving semantic understanding and downstream task performance.

Contribution

SLIP introduces a flexible, language-informed pretraining method that generalizes sensor models across various setups without retraining, combining contrastive alignment with captioning.

Findings

Achieves 77.14% linear-probing accuracy, outperforming baselines.

Demonstrates effective zero-shot transfer across 11 datasets.

Reaches 64.83% accuracy in sensor-based question answering.

Abstract

Modern sensing systems generate large volumes of unlabeled multivariate time-series data. This abundance of unlabeled data makes self-supervised learning (SSL) a natural approach for learning transferable representations. However, most existing approaches are optimized for reconstruction or forecasting objectives and often fail to capture the semantic structure required for downstream classification and reasoning tasks. While recent sensor-language alignment methods improve semantic generalization through captioning and zero-shot transfer, they are limited to fixed sensor configurations, such as predefined channel sets, signal lengths, or temporal resolutions, which hinders cross-domain applicability. To address these gaps, we introduce \textbf{SLIP} (\textbf{S}ensor \textbf{L}anguage-\textbf{I}nformed \textbf{P}retraining), an open-source framework for learning language-aligned representations that generalize across diverse sensor setups. SLIP integrates contrastive alignment with sensor-conditioned captioning, facilitating both discriminative understanding and generative reasoning. By repurposing a pretrained decoder-only language model via cross-attention and introducing an elegant, flexible patch-embedder, SLIP supports different temporal resolutions and variable-length input at inference time without additional retraining. Across 11 datasets, SLIP demonstrates superior performance in zero-shot transfer, signal captioning, and question answering. It achieves a 77.14% average linear-probing accuracy, a 5.93% relative improvement over strong baselines, and reaches 64.83% accuracy in sensor-based question answering.