By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917788967239680 |
|---|---|
| author | Yoon, Hyungjun Tolera, Biniyam Aschalew Gong, Taesik Lee, Kimin Lee, Sung-Ju |
| author_facet | Yoon, Hyungjun Tolera, Biniyam Aschalew Gong, Taesik Lee, Kimin Lee, Sung-Ju |
| contents | 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 times. 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10385 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting Yoon, Hyungjun Tolera, Biniyam Aschalew Gong, Taesik Lee, Kimin Lee, Sung-Ju Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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 times. 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. |
| title | By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.10385 |