By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting

Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance degradation when handling long sensor data sequences. We propose a visual prompting approach for sensor data using multimodal LLMs (MLLMs). We design a visual prompt that directs MLLMs to utilize visualized sensor data alongside the target sensory task descriptions. Additionally, we introduce a visualization generator that automates the creation of optimal visualizations tailored to a given sensory task, eliminating the need for prior task-specific knowledge. We evaluated our approach on nine sensory tasks involving four sensing modalities, achieving an average of 10% higher accuracy than text-based prompts and reducing token costs by 15.8×. Our findings highlight the effectiveness and cost-efficiency of visual prompts with MLLMs for various sensory tasks. The source code is available at https://github. com/diamond264/ByMyEyes . significant applications, ranging from authentication (Abuhamad et al., 2020) and healthcare (Wang et al., 2019) to agriculture (Sishodia et al., 2020) and environmental monitoring (Feng et al., 2019) . However, MLLMs remain underutilized. The diversity of sensors (Wang et al., 2019) and the heterogeneity among them (Stisen et al., 2015) hinder the implementation of a foundational model that generalizes across various sensing tasks. The expensive data collection (Vijayan et al., 2021) often results in insufficient training data, further complicating the development of such capability. Recent studies explored leveraging pre-trained LLMs to solve general sensory tasks (Yu et al., 2023; Liu et al., 2023; Kim et al., 2024). One approach extracts task-specific features from sensor data and composes them as prompts (Yu et al.,