# VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things

arXiv: https://arxiv.org/abs/2312.00401 · HTML: https://mlsanity.com/paper/2312.00401/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2023.

## Built on by (most cited first, 4 of 4)

- [Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage](https://mlsanity.com/paper/2412.15606/) (2024)
- [CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update](https://mlsanity.com/paper/2312.10908/) (2023)
- [FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models](https://mlsanity.com/paper/2407.11522/) (2024)
- [Perceive What Matters: Relevance-Driven Scheduling for Multimodal Streaming Perception](https://mlsanity.com/paper/2603.13176/) (2026)

## Abstract (arXiv)

Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data. How to schedule the domain-specific perceiving models and analyze the collected videos uniformly, efficiently, and especially intelligently to accomplish complicated tasks is challenging. To address the challenge, we build VIoTGPT, the framework based on LLMs to correctly interact with humans, query knowledge videos, and invoke vision models to analyze multimedia data collaboratively. To support VIoTGPT and related future works, we meticulously crafted the VIoT-Tool dataset, including the training dataset and the benchmark involving 11 representative vision models across three categories based on semi-automatic annotations. To guide LLM to act as the intelligent agent towards intelligent VIoT, we resort to the ReAct instruction tuning method based on VIoT-Tool to learn the tool capability. Quantitative and qualitative experiments and analyses demonstrate the effectiveness of VIoTGPT. We believe VIoTGPT contributes to improving human-centered experiences in VIoT applications. The project website is https://github.com/zhongyy/VIoTGPT.